@article{zhang:jmlr22,
  title = "Truncated Emphatic Temporal Difference Methods for Prediction and Control",
  author = "Shangtong Zhang and Shimon Whiteson",
  year = "2022",
  journal = "Journal of Machine Learning Research",
  number = "153",
  pages = "1--59",
  url = "http://jmlr.org/papers/v23/21-0934.html",
  volume = "23",
}
@inproceedings{sun:aaai22,
  title = "Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency",
  author = "Mingfei Sun and Sam Devlin and Katja Hofmann and Shimon Whiteson",
  year = "2022",
  booktitle = "AAAI 2022: Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence",
  month = "February",
  url = "https://arxiv.org/abs/2112.06054",
}
@article{zintgraf:jmlr21,
  title = "VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning",
  author = "Luisa Zintgraf and Sebastian Schulze and Cong Lu and Leo Feng and Maximilian Igl and Kyriacos Shiarlis and Yarin Gal and Katja Hofmann and Shimon Whiteson",
  year = "2021",
  journal = "Journal of Machine Learning Research",
  pages = "1-39",
  url = "https://jmlr.org/papers/volume22/21-0657/21-0657.pdf",
  volume = "22(289)",
}
@inproceedings{fellows:neurips21,
  title = "Bayesian Bellman Operators",
  author = "Matthew Fellows and Kristian Hartikainen and Shimon Whiteson",
  year = "2021",
  booktitle = "NeurIPS 2021: Proceedings of the Thirty-fifth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "https://openreview.net/pdf?id=_MQBBpJzoZd",
}
@inproceedings{peng:neurips21,
  title = "FACMAC: Factored Multi-Agent Centralised Policy Gradients",
  author = "Bei Peng and Tabish Rashid and Christian Schroeder de Witt and Pierre-Alexandre Kamienny and Philip Torr and Wendelin Boehmer and Shimon Whiteson",
  year = "2021",
  booktitle = "NeurIPS 2021: Proceedings of the Thirty-fifth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "https://openreview.net/pdf?id=WxH774N0mEu",
}
@inproceedings{pan:neurips21,
  title = "Regularized Softmax Deep Multi-Agent Q-Learning",
  author = "Ling Pan and Tabish Rashid and Bei Peng and Longbo Huang and Shimon Whiteson",
  year = "2021",
  booktitle = "NeurIPS 2021: Proceedings of the Thirty-fifth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "https://openreview.net/pdf?id=BGS3o8SpjI3",
}
@inproceedings{blake:neurips21,
  title = "Snowflake: Scaling GNNs to high-dimensional continuous control via parameter freezing",
  author = "Charlie Blake and Vitaly Kurin and Maximilian Igl and Shimon Whiteson",
  year = "2021",
  booktitle = "NeurIPS 2021: Proceedings of the Thirty-fifth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "https://openreview.net/pdf?id=REjT_c1Eejk",
}
@inproceedings{zintgraf:icml21,
  title = "Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning",
  author = "Zintgraf, Luisa M and Feng, Leo and Lu, Cong and Igl, Maximilian and Hartikainen, Kristian and Hofmann, Katja and Whiteson, Shimon",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "12991--13001",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/zintgraf21a.html",
  volume = "139",
}
@inproceedings{zhang:icml21b,
  title = "Breaking the Deadly Triad with a Target Network",
  author = "Zhang, Shangtong and Yao, Hengshuai and Whiteson, Shimon",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "12621--12631",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/zhang21y.html",
  volume = "139",
}
@inproceedings{zhang:icml21a,
  title = "Average-Reward Off-Policy Policy Evaluation with Function Approximation",
  author = "Zhang, Shangtong and Wan, Yi and Sutton, Richard S and Whiteson, Shimon",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "12578--12588",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/zhang21u.html",
  volume = "139",
}
@inproceedings{mahajan:icml21,
  title = "Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning",
  author = "Mahajan, Anuj and Samvelyan, Mikayel and Mao, Lei and Makoviychuk, Viktor and Garg, Animesh and Kossaifi, Jean and Whiteson, Shimon and Zhu, Yuke and Anandkumar, Animashree",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "7301--7312",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/mahajan21a.html",
  volume = "139",
}
@inproceedings{iqbal:icml21,
  title = "Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning",
  author = "Iqbal, Shariq and De Witt, Christian A Schroeder and Peng, Bei and Boehmer, Wendelin and Whiteson, Shimon and Sha, Fei",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "4596--4606",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/iqbal21a.html",
  volume = "139",
}
@inproceedings{gupta:icml21,
  title = "UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning",
  author = "Gupta, Tarun and Mahajan, Anuj and Peng, Bei and Boehmer, Wendelin and Whiteson, Shimon",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "3930--3941",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/gupta21a.html",
  volume = "139",
}
@article{:castellini:jaamas21,
  title = "Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning",
  author = "Jacopo Castellini and Frans Oliehoek and Rahul Savani and Shimon Whiteson",
  year = "2021",
  journal = "Autonomous Agents and Multi-Agent Systems",
  number = "2",
  url = "https://link.springer.com/content/pdf/10.1007/s10458-021-09506-w.pdf",
  volume = "35",
}
@inproceedings{zhang:aaai21,
  title = "Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning",
  author = "Shangtong Zhang and Bo Liu and Shimon Whiteson",
  year = "2021",
  booktitle = "AAAI 2021: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence",
  month = "February",
  url = "https://arxiv.org/pdf/2004.10888",
}
@inproceedings{igl:iclr2021,
  title = "Transient Non-stationarity and Generalisation in Deep Reinforcement Learning",
  author = "Maximilian Igl and Gregory Farquhar and Jelena Luketina and Wendelin Boehmer and Shimon Whiteson",
  year = "2021",
  booktitle = "ICLR 2021: Proceedings of the ninth International Conference on Learning Representations",
  month = "May",
  url = "https://openreview.net/pdf?id=Qun8fv4qSby",
}
@inproceedings{kurin:iclr2021,
  title = "My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control",
  author = "Vitaly Kurin and Maximilian Igl and Tim Rocktachel and Wendelin Boehmer and Shimon Whiteson",
  year = "2021",
  booktitle = "ICLR 2021: Proceedings of the ninth International Conference on Learning Representations",
  month = "May",
  url = "https://openreview.net/pdf?id=N3zUDGN5lO",
}
@inproceedings{wang:iclr2021,
  title = "RODE: Learning Roles to Decompose Multi-Agent Tasks",
  author = "Tonghan Wang and Tarun Gupta and Anuj Mahajan and Bei Peng and Shimon Whiteson and Chongjie Zhang",
  year = "2021",
  booktitle = "ICLR 2021: Proceedings of the ninth International Conference on Learning Representations",
  month = "May",
  url = "https://openreview.net/pdf?id=TTUVg6vkNjK",
}
@article{rashid:jmlr20,
  title = "Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning",
  author = "Tabish Rashid and Mikayel Samvelyan and Christian Schroeder de Witt and Gregory Farquhar and Jakob Foerster and Shimon Whiteson",
  year = "2020",
  journal = "Journal of Machine Learning Research",
  pages = "1-51",
  url = "https://jmlr.org/papers/volume21/20-081/20-081.pdf",
  volume = "21(178)",
}
@inproceedings{zhang:nips20,
  title = "Learning Retrospective Knowledge with Reverse Reinforcement Learning",
  author = "Shangtong Zhang and Vivek Veeriah and Shimon Whiteson",
  year = "2020",
  booktitle = "NeurIPS 2020: Proceedings of the Thirty-fourth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zhangnips20.pdf",
}
@inproceedings{rashid:nips20,
  title = "Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning",
  author = "Tabish Rashid and Gregory Farquhar and Bei Peng and Shimon Whiteson",
  year = "2020",
  booktitle = "NeurIPS 2020: Proceedings of the Thirty-fourth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/rashidnips20.pdf",
}
@inproceedings{kurin:nips20,
  title = "Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?",
  author = "Vitaly Kurin and Saad Godil and Shimon Whiteson and Bryan Catanzaro",
  year = "2020",
  booktitle = "NeurIPS 2020: Proceedings of the Thirty-fourth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/kurinnips20.pdf",
}
@inproceedings{zhang:icml20b,
  title = "Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation",
  author = "Shangtong Zhang and Bo Liu and Hengshuai Yao and Shimon Whiteson",
  year = "2020",
  booktitle = "ICML 2020: Proceedings of the Thirty-Seventh International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zhangicml20b.pdf",
}
@inproceedings{zhang:icml20a,
  title = "GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values",
  author = "Shangtong Zhang and Bo Liu and Shimon Whiteson",
  year = "2020",
  booktitle = "ICML 2020: Proceedings of the Thirty-Seventh International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zhangicml20a.pdf",
}
@inproceedings{boehmer:icml20,
  title = "Deep Coordination Graphs",
  author = "Wendelin Boehmer and Vitaly Kurin and Shimon Whiteson",
  year = "2020",
  booktitle = "ICML 2020: Proceedings of the Thirty-Seventh International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/boehmericml20.pdf",
}
@inproceedings{farquhar:icml20,
  title = "Growing Action Spaces",
  author = "Gregory Farquhar and Laura Gustafson and Zeming Lin and Shimon Whiteson and Nicolas Usunier and Gabriel Synnaeve",
  year = "2020",
  booktitle = "ICML 2020: Proceedings of the Thirty-Seventh International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/farquharicml20.pdf",
}
@article{ciosek:jmlr20,
  title = "Expected Policy Gradients for Reinforcement Learning",
  author = "Kamil Ciosek and Shimon Whiteson",
  year = "2020",
  journal = "Journal of Machine Learning Research",
  pages = "1-51",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/ciosekjmlr20.pdf",
  volume = "21(52)",
}
@inproceedings{zhang:aamas20,
  title = "Deep Residual Reinforcement Learning",
  author = "Shangtong Zhang and Wendelin Boehmer and Shimon Whiteson",
  year = "2020",
  booktitle = "AAMAS 2020: Proceedings of the Nineteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  note = "\textbf{Awarded Best Paper}.",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zhangaamas20.pdf",
}
@inproceedings{satsangi:aamas20,
  title = "Maximizing Information Gain in Partially Observable Environments via Prediction Rewards",
  author = "Yash Satsangi and Sungsu Lim and Shimon Whiteson and Frans Oliehoek and Martha White",
  year = "2020",
  booktitle = "AAMAS 2020: Proceedings of the Nineteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangiaamas20.pdf",
}
@inproceedings{rashid:iclr2020,
  title = "Optimistic Exploration Even With A Pessimistic Initialisation",
  author = "Tabish Rashid and Bei Peng and Wendelin Boehmer and Shimon Whiteson",
  year = "2020",
  booktitle = "ICLR 2020: Proceedings of the Eighth International Conference on Learning Representations",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/rashidiclr20.pdf",
}
@inproceedings{zintgraf:iclr2020,
  title = "VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning",
  author = "Luisa Zintgraf and Kyriacos Shiarlis and Maximilian Igl and Sebastian Schulze and Yarin Gal and Katja Hofmann and Shimon Whiteson",
  year = "2020",
  booktitle = "ICLR 2020: Proceedings of the Eighth International Conference on Learning Representations",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zintgraficlr20.pdf",
}
@inproceedings{schroeder:nips19,
  title = "Multi-Agent Common Knowledge Reinforcement Learning",
  author = "Christian Schroeder de Witt and Jakob Foerster and Gregory Farquhar and Philip H. S. Torr and Wendelin Boehmer and Shimon Whiteson",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/schroederNeurIPS19.pdf",
}
@inproceedings{mahajan:nips19,
  title = "MAVEN: Multi-Agent Variational Exploration",
  author = "Anuj Mahajan and Tabish Rashid and Mikayel Samvelyan and Shimon Whiteson",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/mahajannips19.pdf",
}
@inproceedings{farquhar:nips19,
  title = "Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning",
  author = "Gregory Farquhar and Shimon Whiteson and Jakob Foerster",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/farquharnips19.pdf",
}
@inproceedings{fellows:nips19,
  title = "VIREL: A Variational Inference Framework for Reinforcement Learning",
  author = "Matthew Fellows and Anuj Mahajan and Tim Rudner and Shimon Whiteson",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/fellowsnips19.pdf",
}
@inproceedings{zhang:nips19a,
  title = "DAC: The Double Actor-Critic Architecture for Learning Options",
  author = "Shangtong Zhang and Shimon Whiteson",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zhangnips19a.pdf",
}
@inproceedings{zhang:nips19b,
  title = "Generalized Off-Policy Actor-Critic",
  author = "Shangtong Zhang and Wendelin Boehmer and Shimon Whiteson",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zhangnips19b.pdf",
}
@inproceedings{paul:nips19,
  title = "Fast Efficient Hyperparameter Tuning for Policy Gradient Methods",
  author = "Supratik Paul and Vitaly Kurin and Shimon Whiteson",
  year = "2019",
  booktitle = "NeurIPS 2019: Proceedings of the Thirty-third Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/paulnips19.pdf",
}
@inproceedings{luketina:ijcai19,
  title = "A Survey of Reinforcement Learning Informed by Natural Language",
  author = "Jelena Luketina and Nantas Nardelli and Gregory Farquhar and Jakob Foerster and Jacob Andreas and Edward Grefenstette and Shimon Whiteson and Tim Rocktaschel",
  year = "2019",
  booktitle = "IJCAI 2019: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence",
  month = "August",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/luketinaijcai19.pdf",
}
@inproceedings{mao:icml19,
  title = "A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs",
  author = "Jingkai Mao and Jakob Foerster and Tim Rockt{\"a}schel and Maruan Al-Shedivat and Gregory Farquhar and Shimon Whiteson",
  year = "2019",
  booktitle = "ICML 2019: Proceedings of the Thirty-Sixth International Conference on Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/maoicml19.pdf",
}
@inproceedings{paul:icml19,
  title = "Fingerprint Policy Optimisation for Robust Reinforcement Learning",
  author = "Supratik Paul and Michael A. Osborne and Shimon Whiteson",
  year = "2019",
  booktitle = "ICML 2019: Proceedings of the Thirty-Sixth International Conference on Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/paulicml19.pdf",
}
@inproceedings{zintgraf:icml19,
  title = "Fast Context Adaptation via Meta-Learning",
  author = "Luisa Zintgraf and Kyriacos Shiarlis and Vitaly Kurin and Katja Hofmann and Shimon Whiteson",
  year = "2019",
  booktitle = "ICML 2019: Proceedings of the Thirty-Sixth International Conference on Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zintgraficml19.pdf",
}
@inproceedings{foerster:icml19,
  title = "Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning",
  author = "Jakob N. Foerster and H. Francis Song and Edward Hughes and Neil Burch and Iain Dunning and Shimon Whiteson and Matthew M. Botvinick and Michael Bowling",
  year = "2019",
  booktitle = "ICML 2019: Proceedings of the Thirty-Sixth International Conference on Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foerstericml19.pdf",
}
@inproceedings{mao:icml19,
  title = "A Baseline for Any Order Gradient Estimation\\in Stochastic Computation Graphs",
  author = "Jingkai Mao and Jakob Foerster and Tim Rockt{\"a}schel and Maruan Al-Shedivat and Gregory Farquhar and Shimon Whiteson",
  year = "2019",
  booktitle = "ICML 2019: Proceedings of the Thirty-Sixth International Conference on Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/maoicml19.pdf",
}
@inproceedings{behbahani:icra19,
  title = "Learning from Demonstration in the Wild",
  author = "Feryal Behbahani and Kyriacos Shiarlis and Xi Chen and Vitaly Kurin and Sudhanshu Kasewa and Ciprian Stirbu and Joao Gomes and Supratik Paul and Frans Oliehoek and Joao Messias and Shimon Whiteson",
  year = "2019",
  booktitle = "ICRA 2019: Proceedings of the 2019 IEEE International Conference on Robotics and Automation",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/bebahaniicra19.pdf",
}
@inproceedings{letcher:iclr2019,
  title = "Stable Opponent Shaping in Differentiable Games",
  author = "Alistair Letcher and Jakob Foerster and David Balduzzi and Tim Rocktaschel and Shimon Whiteson",
  year = "2019",
  booktitle = "ICLR 2019: Proceedings of the Seventh International Conference on Learning Representations",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/letchericlr19.pdf",
}
@inproceedings{shiarlis:icml18,
  title = "TACO: Learning Task Decomposition via Temporal Alignment for Control",
  author = "Kyriacos Shiarlis and Markus Wulfmeier and Sasha Salter and Shimon Whiteson and Ingmar Posner",
  year = "2018",
  booktitle = "ICML 2018: Proceedings of the Thirty-Fifth International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/shiarlisicml18.pdf",
}
@inproceedings{rashid:icml18,
  title = "QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning",
  author = "Tabish Rashid and Mikayel Samvelyan and Christian Schroeder de Witt and Gregory Farquhar and Jakob Foerster and Shimon Whiteson",
  year = "2018",
  booktitle = "ICML 2018: Proceedings of the Thirty-Fifth International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/rashidicml18.pdf",
}
@inproceedings{igl:icml18,
  title = "Deep Variational Reinforcement Learning for POMDPs",
  author = "Maximillian Igl and Luisa Zintgraf and Tuan Anh Le and Frank Wood and Shimon Whiteson",
  year = "2018",
  booktitle = "ICML 2018: Proceedings of the Thirty-Fifth International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/iglicml18.pdf",
}
@inproceedings{fellows:icml18,
  title = "Fourier Policy Gradients",
  author = "Matthew Fellows and Kamil Ciosek and Shimon Whiteson",
  year = "2018",
  booktitle = "ICML 2018: Proceedings of the Thirty-Fifth International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/fellowsicml18.pdf",
}
@inproceedings{foerster:icml18,
  title = "DiCE: The Infinitely Differentiable Monte Carlo Estimator",
  author = "Jakob Foerster and Gregory Farquhar and Maruan Al-Shedivat and Tim Rocktaschel and Eric P. Xing and Shimon Whiteson",
  year = "2018",
  booktitle = "ICML 2018: Proceedings of the Thirty-Fifth International Conference on Machine Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foerstericml18.pdf",
}
@inproceedings{farquhar:iclr218,
  title = "TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning",
  author = "Gregory Farquhar and Tim Rocktaschel and Maximilian Igl and Shimon Whiteson",
  year = "2018",
  booktitle = "ICLR 2018: Proceedings of the Sixth International Conference on Learning Representations",
  month = "April",
  url = "https://openreview.net/pdf?id=H1dh6Ax0Z",
}
@inproceedings{foerster:aamas18,
  title = "Learning with Opponent-Learning Awareness",
  author = "Jakob Foerster and Richard Chen and Maruan Al-Shedivat and Shimon Whiteson and Pieter Abbeel and Igor Mordatch",
  year = "2018",
  booktitle = "AAMAS 2018: Proceedings of the Seventeenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foersteraamas18.pdf",
}
@article{li:jaamas18,
  title = "Social Interaction for Efficient Agent Learning from Human Reward",
  author = "Guangliang Li and Shimon Whiteson and W. Bradley Knox and Hayley Hung",
  year = "2018",
  journal = "Autonomous Agents and Multi-Agent Systems",
  number = "1",
  pages = "1-25",
  url = "http://rdcu.be/tTq8",
  volume = "32",
}
@inproceedings{paul:aaai18,
  title = "Alternating Optimisation and Quadrature for Robust Control",
  author = "Supratik Paul and Konstantinos Chatzilygeroudis and Kamil Ciosek and Jean-Baptiste Mouret and Michael Osborne and Shimon Whiteson",
  year = "2018",
  booktitle = "AAAI 2018: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence",
  month = "February",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/paulaaai18.pdf",
}
@inproceedings{foerster:aaai18,
  title = "Counterfactual Multi-Agent Policy Gradients",
  author = "Jakob Foerster and Gregory Farquhar and Triantafyllos Afouras and Nantas Nardelli and Shimon Whiteson",
  year = "2018",
  booktitle = "AAAI 2018: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence",
  month = "February",
  note = "\textbf{Awarded Outstanding Student Paper}.",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foersteraaai18.pdf",
}
@inproceedings{ciosek:aaai18,
  title = "Expected Policy Gradients",
  author = "Kamil Ciosek and Shimon Whiteson",
  year = "2018",
  booktitle = "AAAI 2018: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence",
  month = "February",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/ciosekaaai18.pdf",
}
@inproceedings{messias:nips17,
  title = "Dynamic-Depth Context Tree Weighting",
  author = "Jo\~{a}o Messias and Shimon Whiteson",
  year = "2017",
  booktitle = "NeurIPS 2017: Proceedings of the Thirty-First Annual Conference on Neural Information Processing Systems",
  month = "December",
  note = "\textbf{NVAIL Pioneering Research Award}.",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/messiasnips17.pdf",
}
@inproceedings{satsangi:uai17,
  title = "Real-Time Resource Allocation for Tracking Systems",
  author = "Yash Satsangi and Shimon Whiteson and Frans Oliehoek and Henri Bouma",
  year = "2017",
  booktitle = "UAI 2017: Proceedings of the Conference on Uncertainty in Artificial Intelligence",
  month = "July",
  pages = "3220-3227",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangiuai17.pdf",
}
@article{satsangi:ar17,
  title = "Exploiting submodular value functions for scaling up active perception",
  author = "Yash Satsangi and Shimon Whiteson and Frans Oliehoek and Matthijs Spaan",
  year = "2017",
  journal = "Autonomous Robots",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangiar17.pdf",
}
@article{li:jaamas17,
  title = "Social Interaction for Efficient Agent Learning from Human Reward",
  author = "Guangliang Li and Shimon Whiteson and W. Bradley Knox and Hayley Hung",
  year = "2017",
  journal = "Autonomous Agents and Multi-Agent Systems",
  note = "To appear.",
  url = "http://rdcu.be/tTq8",
}
@inproceedings{shiarlis:iros17,
  title = "Acquiring Social Interaction Behaviours for Telepresence Robots via Deep Learning from Demonstration",
  author = "Kyriacos Shiarlis and Jo\~{a}o Messias and Shimon Whiteson",
  year = "2017",
  booktitle = "IROS 2017: Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems",
  month = "September",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/shiarlisiros17.pdf",
}
@inproceedings{foerster:icml17,
  title = "Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning",
  author = "Jakob Foerster and Nantas Nardelli and Greg Farquhar and Phil Torr and Pushmeet Kohli and Shimon Whiteson",
  year = "2017",
  booktitle = "ICML 2017: Proceedings of the Thirty-Fourth International Conference on Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foerstericml17.pdf",
}
@book{roijers:book17,
  title = "Multi-Objective Decision Making",
  author = "Diederik Roijers and Shimon Whiteson",
  year = "2017",
  address = "California, USA",
  note = "doi:10.2200/S00765ED1V01Y201704AIM034",
  publisher = "Morgan and Claypool",
  series = "Synthesis Lectures on Artificial Intelligence and Machine Learning",
  url = "http://www.morganclaypool.com/doi/abs/10.2200/S00765ED1V01Y201704AIM034",
}
@inproceedings{shiarlis:icra17,
  title = "Rapidly Exploring Learning Trees",
  author = "Kyriacos Shiarlis and Jo\~{a}o Messias and Shimon Whiteson",
  year = "2017",
  booktitle = "ICRA 2017: Proceedings of the 2017 IEEE International Conference on Robotics and Automation",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/shiarlisicra17.pdf",
}
@inproceedings{ciosek:aaai17,
  title = "OFFER: Off-Environment Reinforcement Learning",
  author = "Kamil Ciosek and Shimon Whiteson",
  year = "2017",
  booktitle = "AAAI 2017: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence",
  month = "February",
  pages = "1819-1825",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/ciosekaaai17.pdf",
}
@inproceedings{satsangi:uai17,
  title = "Real-Time Resource Allocation for Tracking Systems",
  author = "Yash Satsangi and Shimon Whiteson and Frans Oliehoek and Henri Bouma",
  year = "2016",
  booktitle = "UAI 2017: Proceedings of the Conference on Uncertainty in Artificial Intelligence",
  month = "July",
  pages = "3220-3227",
  url = "To appear.",
}
@article{li:jaamas15,
  title = "Using Informative Behavior to Increase Engagement while Learning from Human Reward",
  author = "Guangliang Li and Shimon Whiteson and W. Bradley Knox and Hayley Hung",
  year = "2016",
  journal = "Autonomous Agents and Multi-Agent Systems",
  number = "5",
  pages = "826-848",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/lijaamas15.pdf",
  volume = "30",
}
@inproceedings{foerster:nips16,
  title = "Learning to Communicate with Deep Multi-Agent Reinforcement Learning",
  author = "Jakob Foerster and Yannis Assael and Nando de Freitas and Shimon Whiteson",
  year = "2016",
  booktitle = "NeurIPS 2016: Proceedings of the Thirtieth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foersternips16.pdf",
}
@inproceedings{satsangi:ijcai15,
  title = "{PAC} Greedy Maximization with Efficient Bounds on Information Gain for Sensor Selection",
  author = "Yash Satsangi and Shimon Whiteson and Frans Oliehoek",
  year = "2016",
  booktitle = "IJCAI 2016: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence",
  month = "July",
  pages = "3220-3227",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangiijcai16.pdf",
}
@inproceedings{shiarlis:aamas16,
  title = "Inverse Reinforcement Learning from Failure",
  author = "Kyriacos Shiarlis and Jo\~{a}o Messias and Shimon Whiteson",
  year = "2016",
  booktitle = "AAMAS 2016: Proceedings of the Fifteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  note = "\textbf{Nominated for Best Student Paper}.",
  pages = "1060-1068",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/shiarlisaamas16.pdf",
}
@inproceedings{zoghi:wsdm15,
  title = "Multileave Gradient Descent for Fast Online Learning to Rank",
  author = "Anne Schuth and Harrie Oosterhuis and Shimon Whiteson and Maarten de Rijke",
  year = "2016",
  booktitle = "WSDM 2016: Proceedings of the Ninth ACM International Conference on Web Search and Data Mining",
  month = "February",
  pages = "457-466",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/schuthwsdm16.pdf",
}
@inproceedings{roijers:nips15,
  title = "Variational Multi-Objective Coordination",
  author = "Diederik Roijers and Shimon Whiteson and Alex Ihler and Frans Oliehoek",
  year = "2015",
  booktitle = "NeurIPS 2015: Proceedings of the Twenty-Ninth Annual Conference on Neural Information Processing Systems, Workshop on Learning, Inference and Control of Multi-Agent Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersnips15.pdf",
}
@techreport{satsangi:tr15,
  title = "An Analysis of Piecewise-Linear and Convex Value Functions for Active Perception {POMDP}s",
  author = "Yash Satsangi and Shimon Whiteson and Matthijs T. J. Spaan",
  year = "2015",
  institution = "University of Amsterdam, Informatics Institute",
  number = "IAS-UVA-15-01",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangitr15.pdf",
}
@inproceedings{dewaard:bnaic15,
  title = "Queued Pareto Local Search for Multi-objective Decision Making",
  author = "Maarten de Waard and Maarten Inja and Chiel Kooijman and Diederik Roijers and Shimon Whiteson",
  year = "2015",
  booktitle = "BNAIC 2015: Proceedings of the Twenty-Seventh Benelux Conference on Artificial Intelligence",
  month = "November",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/dewaardbnaic15.pdf",
}
@inproceedings{zoghi:nips15,
  title = "Copeland Dueling Bandits",
  author = "Masrour Zoghi and Zohar Karnin and Shimon Whiteson and Maarten de Rijke",
  year = "2015",
  booktitle = "NeurIPS 2015: Proceedings of the Twenty-Ninth Annual Conference on Neural Information Processing Systems",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zoghinips15.pdf",
}
@inproceedings{kooijman:esann15,
  title = "Pareto Local Policy Search for MOMDP Planning",
  author = "Chiel Kooijman and Maarten de Waard and Maarten Inja and Diederik Roijers and Shimon Whiteson",
  year = "2015",
  booktitle = "ESANN 2015: Proceedings of the 23rd European Symposium on Artificial Neural Networks, Special Session on Emerging Techniques and Applications in Multi-Objective Reinforcement Learning",
  month = "April",
  pages = "53-58",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/kooijmanesann15.pdf",
}
@inproceedings{li:aamas15,
  title = "A Large-Scale Study of Agents Learning from Human Reward",
  author = "Guangliang Li and Hayley Hung and Shimon Whiteson",
  year = "2015",
  booktitle = "AAMAS 2015: Proceedings of the Fourteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  note = "Extended Abstract.",
  pages = "1771-1772",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/liaamas15.pdf",
}
@inproceedings{shiarlis:icra15,
  title = "TERESA: A Socially Intelligent Semi-autonomous Telepresence System",
  author = "Kyriacos Shiarlis and Joao Messias and Maarten van Someren and Shimon Whiteson and Jaebok Kim and Jered Vroon and Gwenn Englebienne and Khiet Truong and Vanessa Evers and Noe Perez-Higueras and Ignacio Perez-Hurtado and Rafael Ramon-Vigo and Fernando Caballero and Luis Merino and Jie Shen and Stavros Petridis and Maja Pantic and Lasse Hedman and Marten Scherlund and Raphael Koster and Herve Michel",
  year = "2015",
  booktitle = "ICRA 2015: Proceedings of the IEEE International Conference on Robotics and Automation, Workshop on Machine Learning for Social Robotics",
  month = "May",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/shiarlisicra15.pdf",
}
@inproceedings{shiarlis:rss15,
  title = "Inverse Reinforcement Learning from Failure",
  author = "Kyriacos Shiarlis and Joao Messias and Maarten van Someren and Shimon Whiteson",
  year = "2015",
  booktitle = "RSS 2015: Proceedings of the 2015 Robotics: Science and Systems Conference, Workshop on Learning from Demonstration: Inverse Optimal Control, Reinforcement Learning, and Lifelong Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/shiarlisrss15.pdf",
}
@inproceedings{roijers:ewrl15,
  title = "Why Multi-Objective Reinforcement Learning?",
  author = "Diederik Roijers and Shimon Whiteson and Peter Vamplew and Richard Dazeley",
  year = "2015",
  booktitle = "EWRL 2015: Proceedings of the Twelfth European Workshop on Reinforcement Learning",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersewrl15.pdf",
}
@article{roijers:jair15,
  title = "Computing Convex Coverage Sets for Faster Multi-Objective Coordination",
  author = "Diederik Roijers and Shimon Whiteson and Frans Oliehoek",
  year = "2015",
  journal = "Journal of Artificial Intelligence Research",
  pages = "399-443",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersjair15.pdf",
  volume = "52",
}
@inproceedings{zoghi:wsdm15,
  title = "{MergeRUCB}: A Method for Large-Scale Online Ranker Evaluation",
  author = "Masrour Zoghi and Shimon Whiteson and Maarten de Rijke",
  year = "2015",
  booktitle = "WSDM 2015: Proceedings of the Eighth ACM International Conference on Web Search and Data Mining",
  month = "February",
  pages = "17-26",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zoghiwsdm15.pdf",
}
@inproceedings{grotov:sigir15,
  title = "Bayesian Ranker Comparison Based on Historical User Interactions",
  author = "Artem Grotov and Shimon Whiteson and Maarten de Rijke",
  year = "2015",
  booktitle = "SIGIR 2015: Proceedings of the Thirty-Eighth Annual ACM SIGIR Conference",
  month = "August",
  pages = "273-282",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/grotovsigir15.pdf",
}
@inproceedings{satsangi:aaai15,
  title = "Exploiting Submodular Value Functions for Faster Dynamic Sensor Selection",
  author = "Yash Satsangi and Shimon Whiteson and Frans Oliehoek",
  year = "2015",
  booktitle = "AAAI 2015: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence",
  month = "January",
  pages = "3356-3363",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangiaaai15.pdf",
}
@inproceedings{roijers:ijcai15,
  title = "Point-Based Planning for Multi-Objective {POMDPs}",
  author = "Diederik Roijers and Shimon Whiteson and Frans Oliehoek",
  year = "2015",
  booktitle = "IJCAI 2015: Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence",
  month = "July",
  pages = "1666-1672",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersijcai15.pdf",
}
@inproceedings{li:aamas14,
  title = "Leveraging Social Networks to Motivate Humans to Train Agents",
  author = "Guangliang Li and Hayley Hung and Shimon Whiteson and W. Bradley Knox",
  year = "2014",
  booktitle = "AAMAS 2014: Proceedings of the Thirteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  note = "Extended Abstract.",
  pages = "1571-1572",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/liaamas14.pdf",
}
@inproceedings{bakkes:fdg14b,
  title = "Design Criteria for Challenge Balancing of Personalised Game Spaces",
  author = "Sander Bakkes and Shimon Whiteson",
  year = "2014",
  booktitle = "FDG 2014: Proceedings of the Ninth International Conference on the Foundations of Digital Games",
  month = "April",
  note = "Short paper.",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/bakkesfdg14b.pdf",
}
@inproceedings{bakkes:fdg14a,
  title = "Towards Challenge Balancing for Personalised Game Spaces",
  author = "Sander Bakkes and Shimon Whiteson",
  year = "2014",
  booktitle = "FDG 2014: Proceedings of the Ninth International Conference on the Foundations of Digital Games, Workshop on Procedural Content Generation in Games",
  month = "April",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/bakkesfdg14a.pdf",
}
@inproceedings{roijers:bnaic14,
  title = "Bounded Approximations for Linear Multi-Objective Planning under Uncertainty",
  author = "Diederik Roijers and Joris Scharpff and Matthijs Spaan and Frans Oliehoek and Mathijs De Weerdt and Shimon Whiteson",
  year = "2014",
  booktitle = "BNAIC 2014: Proceedings of the Twenty-Sixth Benelux Conference on Artificial Intelligence",
  month = "November",
  pages = "168-169",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersbnaic14.pdf",
}
@techreport{satsangi:tr14,
  title = "Exploiting Submodular Value Functions for Faster Dynamic Sensor Selection: Extended Version",
  author = "Yash Satsangi and Shimon Whiteson and Frans Oliehoek",
  year = "2014",
  institution = "University of Amsterdam, Informatics Institute",
  number = "IAS- UVA-14-02",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/satsangitr14.pdf",
}
@article{hofmann:sigweb14,
  title = "Learning to Rank for Information Retrieval from User Interactions",
  author = "Katja Hofmann and Shimon Whiteson and Anne Schuth and Maarten de Rijke",
  year = "2014",
  journal = "SIGWEB Newsletter",
  month = "April",
  number = "Spring",
  pages = "1-7",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmannsigweb14.pdf",
}
@article{snel:jaamas14,
  title = "Learning Potential Functions and their Representations for Multi-Task Reinforcement Learning",
  author = "Matthijs Snel and Shimon Whiteson",
  year = "2014",
  journal = "Autonomous Agents and Multi-Agent Systems",
  number = "4",
  pages = "637-681",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/sneljaamas14.pdf",
  volume = "28",
}
@article{vanseijen:ci14,
  title = "Efficient Abstraction Selection in Reinforcement Learning",
  author = "Harm van Seijen and Shimon Whiteson and Leon Kester",
  year = "2014",
  journal = "Computational Intelligence",
  number = "4",
  pages = "657-699",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijenci14.pdf",
  volume = "30",
}
@inproceedings{schuth:ecir14,
  title = "Optimizing Base Rankers Using Clicks: A Case Study using {BM25}",
  author = "Anne Schuth and Floor Sietsma and Shimon Whiteson and Maarten de Rijke",
  year = "2014",
  booktitle = "ECIR 2014: Proceedings of the Thirty-Sixth European Conference on Information Retrieval",
  month = "April",
  pages = "75-87",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/schuthecir14.pdf",
}
@inproceedings{inja:ppsn14,
  title = "Queued Pareto Local Search for Multi-Objective Optimization",
  author = "Maarten Inja and Chiel Kooijman and Maarten de Waard and Diederik Roijers and Shimon Whiteson",
  year = "2014",
  booktitle = "PPSN 2014: Proceedings of the Thirteenth International Conference on Parallel Problem Solving from Nature",
  month = "September",
  pages = "589-599",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/injappsn14.pdf",
}
@inproceedings{blom:aiide14,
  title = "Towards Personalised Gaming via Facial Expression Recognition",
  author = "Paris Mavromoustakos Blom and Sander Bakkes and Chek Tien Tan and Shimon Whiteson and Diederik Roijers and Roberto Valenti and Theo Gevers",
  year = "2014",
  booktitle = "AIIDE 2014: Proceedings of the Tenth Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment",
  month = "October",
  pages = "30-36",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/blomaiide14.pdf",
}
@inproceedings{li:icdl14,
  title = "Learning from Human Reward Benefits from Socio-competitive Feedback",
  author = "Guangliang Li and Hayley Hung and Shimon Whiteson and W. Bradley Knox",
  year = "2014",
  booktitle = "ICDL-Epirob 2014: Proceedings of the Fourth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics",
  month = "October",
  pages = "70-77",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/liicdl14.pdf",
}
@inproceedings{bakkes:gem14,
  title = "Challenge Balancing for Personalised Game Spaces",
  author = "Sander Bakkes and Shimon Whiteson and Guangliang Li and George Viorel Visniuc and Efstathios Charitos and Norbert Heijne and Arjen Swellengrebel",
  year = "2014",
  booktitle = "GEM 2014: Proceedings of the IEEE Games, Entertainment, and Media Conference",
  month = "October",
  pages = "38-45",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/bakkesgem14.pdf",
}
@inproceedings{zoghi:wsdm14,
  title = "Using Confidence Bounds for Efficient On-Line Ranker Evaluation",
  author = "Masrour Zoghi and Shimon Whiteson and Maarten de Rijke and Remi Munos",
  year = "2014",
  booktitle = "WSDM 2014: Proceedings of the Seventh ACM International Conference on Web Search and Data Mining",
  month = "February",
  pages = "73-82",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zoghiwsdm14.pdf",
}
@inproceedings{schuth:cikm14,
  title = "Multileaved Comparisons for Fast Online Evaluation",
  author = "Anne Schuth and Floor Sietsma and Shimon Whiteson and Damien Lefortier and Maarten de Rijke",
  year = "2014",
  booktitle = "CIKM 2014: Proceedings of the Twenty-Third Conference on Information and Knowledge Management",
  month = "November",
  pages = "71-80",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/schuthcikm14.pdf",
}
@inproceedings{zoghi:icml14,
  title = "Relative Upper Confidence Bound for the {K}-Armed Dueling Bandit Problem",
  author = "Masrour Zoghi and Shimon Whiteson and Remi Munos and Maarten de Rijke",
  year = "2014",
  booktitle = "ICML 2014: Proceedings of the Thirty-First International Conference on Machine Learning",
  month = "June",
  pages = "10-18",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/zoghiicml14.pdf",
}
@inproceedings{roijers:aamas14,
  title = "Linear Support for Multi-Objective Coordination Graphs",
  author = "Diederik Roijers and Shimon Whiteson and Frans Oliehoek",
  year = "2014",
  booktitle = "AAMAS 2014: Proceedings of the Thirteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  pages = "1297-1304",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersaamas14.pdf",
}
@inproceedings{roijers:icaps14,
  title = "Bounded Approximations for Linear Multi-Objective Planning under Uncertainty",
  author = "Diederik Roijers and Joris Scharpff and Matthijs Spaan and Frans Oliehoek and Mathijs De Weerdt and Shimon Whiteson",
  year = "2014",
  booktitle = "ICAPS 2014: Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling",
  month = "June",
  pages = "262-270",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersicaps14.pdf",
}
@inproceedings{roijers:aamas13,
  title = "Multi-Objective Variable Elimination for Collaborative Graphical Games",
  author = "Diederik Roijers and Shimon Whiteson and Frans Oliehoek",
  year = "2013",
  booktitle = "AAMAS 2013: Proceedings of the Twelfth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  note = "Extended Abstract.",
  pages = "1209-1210",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersaamas13.pdf",
}
@inproceedings{vanseijen:sara13,
  title = "Efficient Abstraction Selection in Reinforcement Learning",
  author = "Harm van Seijen and Shimon Whiteson and Leon Kester",
  year = "2013",
  booktitle = "SARA 2013: Proceedings of the Tenth Symposium on Abstraction, Reformulation, and Approximation",
  month = "July",
  note = "Extended Abstract.",
  pages = "123-127",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijensara13.pdf",
}
@inproceedings{schuth:cikm13,
  title = "Lerot: an Online Learning to Rank Framework",
  author = "Anne Schuth and Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2013",
  booktitle = "CIKM 2013: Proceedings of the Twenty-Second Conference on Information and Knowledge Management, Workshop on Living Labs for Information Retrieval Evaluation",
  month = "November",
  pages = "23-26",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/schuthcikm13.pdf",
}
@inproceedings{oliehoek:bnaic13,
  title = "Approximate Solutions for Factored {Dec-POMDPs} with Many Agents -- Extended Abstract",
  author = "Frans Oliehoek and Shimon Whiteson and Matthijs Spaan",
  year = "2013",
  booktitle = "BNAIC 2013: Proceedings of the Twenty-Fifth Benelux Conference on Artificial Intelligence",
  month = "November",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/oliehoekbnaic13.pdf",
}
@article{hofmann:irj13,
  title = "Balancing Exploration and Exploitation in Listwise and Pairwise Online Learning to Rank for Information Retrieval",
  author = "Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2013",
  journal = "Information Retrieval",
  number = "1",
  pages = "63-90",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmannirj13.pdf",
  volume = "16",
}
@article{oliehoek:jair13,
  title = "Incremental Clustering and Expansion for Faster Optimal Planning in Decentralized {POMDPs}",
  author = "Frans Oliehoek and Matthijs Spaan and Christopher Amato and Shimon Whiteson",
  year = "2013",
  journal = "Journal of Artificial Intelligence Research",
  pages = "449-509",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/oliehoekjair13.pdf",
  volume = "46",
}
@article{hofmann:tois13,
  title = "Fidelity, Soundness, and Efficiency of Interleaved Comparison Methods",
  author = "Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2013",
  journal = "Transactions on Information Systems",
  pages = "17:1-43",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmanntois13.pdf",
  volume = "31(4)",
}
@article{roijers:jair13,
  title = "A Survey of Multi-Objective Sequential Decision-Making",
  author = "Diederik Roijers and Peter Vamplew and Shimon Whiteson and Richard Dazeley",
  year = "2013",
  journal = "Journal of Artificial Intelligence Research",
  pages = "67-113",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersjair13.pdf",
  volume = "48",
}
@inproceedings{vandenberg:gecco13,
  title = "Critical Factors in the Performance of {HyperNEAT}",
  author = "Thomas van den Berg and Shimon Whiteson",
  year = "2013",
  booktitle = "GECCO 2013: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  pages = "759-766",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vandenberggecco13.pdf",
}
@inproceedings{roijers:adt13,
  title = "Computing Convex Coverage Sets for Multi-Objective Coordination Graphs",
  author = "Diederik Roijers and Shimon Whiteson and Frans Oliehoek",
  year = "2013",
  booktitle = "ADT 2013: Proceedings of the Third International Conference on Algorithmic Decision Theory",
  month = "November",
  pages = "309-323",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/roijersadt13.pdf",
}
@inproceedings{hofmann:wsdm13,
  title = "Reusing Historical Interaction Data for Faster Online Learning to Rank for {IR}",
  author = "Katja Hofmann and Anne Schuth and Shimon Whiteson and Maarten de Rijke",
  year = "2013",
  booktitle = "WSDM 2013: Proceedings of the Sixth ACM International Conference on Web Search and Data Mining",
  month = "February",
  pages = "183-192",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmannwsdm13.pdf",
}
@inproceedings{oliehoek:aamas13,
  title = "Approximate Solutions for Factored {Dec-POMDPs} with Many Agents",
  author = "Frans Oliehoek and Shimon Whiteson and Matthijs Spaan",
  year = "2013",
  booktitle = "AAMAS 2013: Proceedings of the Twelfth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  pages = "563-570",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/oliehoekaamas13.pdf",
}
@inproceedings{li:aamas13,
  title = "Using Informative Behavior to Increase Engagement in the {TAMER} Framework",
  author = "Guangliang Li and Hayley Hung and Shimon Whiteson and W. Bradley Knox",
  year = "2013",
  booktitle = "AAMAS 2013: Proceedings of the Twelfth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  pages = "909-916",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/liaamas13.pdf",
}
@inbook{whiteson:rlsota11,
  title = "Evolutionary Computation for Reinforcement Learning",
  author = "Shimon Whiteson",
  year = "2012",
  address = "Berlin, Germany",
  booktitle = "Reinforcement Learning: State of the Art",
  editor = "Marco Wiering and Martijn van Otterlo",
  pages = "325-355",
  publisher = "Springer",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonrlsota11.pdf",
}
@inproceedings{hofmann:cikm12,
  title = "Estimating Interleaved Comparison Outcomes from Historical Click Data",
  author = "Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2012",
  booktitle = "CIKM 2012: Proceedings of the Twenty-First Conference on Information and Knowledge Management",
  month = "October",
  note = "Short paper.",
  pages = "1779-1783",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmanncikm12.pdf",
}
@inproceedings{oliehoek:uai12,
  title = "Exploiting Structure in Cooperative {B}ayesian Games",
  author = "Frans Oliehoek and Shimon Whiteson and Matthijs Spaan",
  year = "2012",
  booktitle = "UAI 2012: Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence",
  month = "August",
  pages = "654-664",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/oliehoekuai12.pdf",
}
@inproceedings{rao:aamas12,
  title = "{V-MAX}: Tempered Optimism for Better {PAC} Reinforcement Learning",
  author = "Karun Rao and Shimon Whiteson",
  year = "2012",
  booktitle = "AAMAS 2012: Proceedings of the Eleventh International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "June",
  pages = "375-382",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/raoaamas12.pdf",
}
@incollection{whiteson:rlsota11,
  title = "Evolutionary Computation for Reinforcement Learning",
  author = "Shimon Whiteson",
  year = "2012",
  address = "Berlin, Germany",
  booktitle = "Reinforcement Learning: State of the Art",
  editor = "Marco Wiering and Martijn van Otterlo",
  pages = "325-355",
  publisher = "Springer",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonrlsota11.pdf",
}
@inproceedings{snel:ewrl11,
  title = "Multi-Task Reinforcement Learning: Shaping and Feature Selection",
  author = "Matthijs Snel and Shimon Whiteson",
  year = "2011",
  booktitle = "EWRL 2011: Proceedings of the Ninth European Workshop on Reinforcement Learning",
  month = "September",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/snelewrl11.pdf",
}
@inproceedings{hofmann:nips11,
  title = "Contextual Bandits for Information Retrieval",
  author = "Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2011",
  booktitle = "NeurIPS 2011: Proceedings of the Conference on Neural Information Processing Systems, Workshop on Bayesian Optimization, Experimental Design and Bandits: Theory and Applications",
  month = "December",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmannnips11.pdf",
}
@article{vanseijen:jmlr11,
  title = "Exploiting Best-Match Equations for Efficient Reinforcement Learning",
  author = "Harm van Seijen and Shimon Whiteson and Hado van Hasselt and Marco Wiering",
  year = "2011",
  journal = "Journal of Machine Learning Research",
  pages = "2045-2094",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijenjmlr11.pdf",
  volume = "12",
}
@article{whiteson:mlj11,
  title = "Introduction to the Special Issue on Empirical Evaluations in Reinforcement Learning",
  author = "Shimon Whiteson and Michael L. Littman",
  year = "2011",
  journal = "Machine Learning",
  number = "1",
  pages = "1-6",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonmlj11.pdf",
  volume = "84",
}
@article{koppejan:ei11,
  title = "Neuroevolutionary Reinforcement Learning for Generalized Control of Simulated Helicopters",
  author = "Rogier Koppejan and Shimon Whiteson",
  year = "2011",
  journal = "Evolutionary Intelligence",
  pages = "219-241",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/koppejanei11.pdf",
  volume = "4",
}
@inproceedings{kistemaker:gecco11,
  title = "Critical Factors in the Performance of Novelty Search",
  author = "Steijn Kistemaker and Shimon Whiteson",
  year = "2011",
  booktitle = "GECCO 2011: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  pages = "965-972",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/kistemakergecco11.pdf",
}
@inproceedings{whiteson:adprl11,
  title = "Protecting Against Evaluation Overfitting in Empirical Reinforcement Learning",
  author = "Shimon Whiteson and Brian Tanner and Matthew E. Taylor and Peter Stone",
  year = "2011",
  booktitle = "ADPRL 2011: Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning",
  month = "April",
  pages = "120-127",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonadprl11.pdf",
}
@inproceedings{hofmann:ecir11,
  title = "Balancing Exploration and Exploitation in Learning to Rank Online",
  author = "Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2011",
  booktitle = "ECIR 2011: Proceedings of the Thirty-Third European Conference on Information Retrieval",
  month = "April",
  pages = "251-263",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmannecir11.pdf",
}
@inproceedings{snel:icdl11,
  title = "Robust Central Pattern Generators for Embodied Hierarchical Reinforcement Learning",
  author = "Matthijs Snel and Shimon Whiteson and Yasuo Kuniyoshi",
  year = "2011",
  booktitle = "ICDL-Epirob 2011: Proceedings of the First Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics",
  month = "August",
  pages = "1-6",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/snelicdl11.pdf",
}
@inproceedings{hofmann:cikm11,
  title = "A Probabilistic Method for Inferring Preferences from Clicks",
  author = "Katja Hofmann and Shimon Whiteson and Maarten de Rijke",
  year = "2011",
  booktitle = "CIKM 2011: Proceedings of the Twentieth Conference on Information and Knowledge Management",
  month = "October",
  pages = "249-258",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/hofmanncikm11.pdf",
}
@inbook{bakker:icis10,
  title = "Traffic Light Control by Multiagent Reinforcement Learning Systems",
  author = "Bram Bakker and Shimon Whiteson and Leon Kester and Frans Groen",
  year = "2010",
  address = "Berlin, Germany",
  booktitle = "Interactive Collaborative Information Systems",
  editor = "Robert Babuska and Frans Groen",
  pages = "475-510",
  publisher = "Springer",
  series = "Studies in Computational Intelligence",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/bakkericis10.pdf",
}
@inbook{vanseijen:icis10,
  title = "Switching between Representations in Reinforcement Learning",
  author = "Harm van Seijen and Shimon Whiteson and Leon Kester",
  year = "2010",
  address = "Berlin, Germany",
  booktitle = "Interactive Collaborative Information Systems",
  editor = "Robert Babuska and Frans Groen",
  pages = "65-84",
  publisher = "Springer",
  series = "Studies in Computational Intelligence",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijenicis10.pdf",
}
@article{whiteson:aim10,
  title = "The Reinforcement Learning Competitions",
  author = "Shimon Whiteson and Brian Tanner and Adam White",
  year = "2010",
  journal = "AI Magazine",
  number = "2",
  pages = "81-94",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonaim10.pdf",
  volume = "31",
}
@article{whiteson:jaamas10,
  title = "Critical Factors in the Empirical Performance of Temporal Difference and Evolutionary Methods for Reinforcement Learning",
  author = "Shimon Whiteson and Matthew E. Taylor and Peter Stone",
  year = "2010",
  journal = "Autonomous Agents and Multi-Agent Systems",
  number = "1",
  pages = "1-27",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonjaamas10.pdf",
  volume = "21",
}
@inproceedings{snel:gecco10,
  title = "Multi-Task Evolutionary Shaping Without Pre-Specified Representations",
  author = "Matthijs Snel and Shimon Whiteson",
  year = "2010",
  booktitle = "GECCO 2010: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  pages = "1031-1038",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/snelgecco10.pdf",
}
@book{whiteson:book10,
  title = "Adaptive Representations for Reinforcement Learning",
  author = "Shimon Whiteson",
  year = "2010",
  address = "Berlin, Germany",
  publisher = "Springer",
  series = "Studies in Computational Intelligence",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonbook10.pdf",
  volume = "291",
}
@incollection{bakker:icis10,
  title = "Traffic Light Control by Multiagent Reinforcement Learning Systems",
  author = "Bram Bakker and Shimon Whiteson and Leon Kester and Frans Groen",
  year = "2010",
  address = "Berlin, Germany",
  booktitle = "Interactive Collaborative Information Systems",
  editor = "Robert Babuska and Frans Groen",
  pages = "475-510",
  publisher = "Springer",
  series = "Studies in Computational Intelligence",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/bakkericis10.pdf",
}
@incollection{vanseijen:icis10,
  title = "Switching between Representations in Reinforcement Learning",
  author = "Harm van Seijen and Shimon Whiteson and Leon Kester",
  year = "2010",
  address = "Berlin, Germany",
  booktitle = "Interactive Collaborative Information Systems",
  editor = "Robert Babuska and Frans Groen",
  pages = "65-84",
  publisher = "Springer",
  series = "Studies in Computational Intelligence",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijenicis10.pdf",
}
@inproceedings{whiteson:icml09,
  title = "Generalized Domains for Empirical Evaluations in Reinforcement Learning",
  author = "Shimon Whiteson and Brian Tanner and Matthew E. Taylor and Peter Stone",
  year = "2009",
  booktitle = "ICML 2009: Proceedings of the Twenty-Sixth International Conference on Machine Learning: Workshop on Evaluation Methods for Machine Learning",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonicml09.pdf",
}
@article{aaltonen:prl09,
  title = "Measurement of the Top Quark Mass with Dilepton Events Selected using Neuroevolution at {CDF}",
  author = "Aaltonen {et al.\ (including Shimon Whiteson)}",
  year = "2009",
  journal = "Physical Review Letters",
  number = "15",
  pages = "2001",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/aaltonenprl09.pdf",
  volume = "102",
}
@article{whiteson:eaai09,
  title = "Machine Learning for Event Selection in High Energy Physics",
  author = "Shimon Whiteson and Daniel Whiteson",
  year = "2009",
  journal = "Engineering Applications of Artificial Intelligence",
  pages = "1203-1217",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesoneaai09.pdf",
  volume = "22",
}
@inproceedings{koppejan:gecco09,
  title = "Neuroevolutionary Reinforcement Learning for Generalized Helicopter Control",
  author = "Rogier Koppejan and Shimon Whiteson",
  year = "2009",
  booktitle = "GECCO 2009: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  pages = "145-152",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/koppejangecco09.pdf",
}
@inproceedings{vanseijen:adprl09,
  title = "A Theoretical and Empirical Analysis of Expected Sarsa",
  author = "Harm van Seijen and Hado van Hasselt and Shimon Whiteson and Marco Wiering",
  year = "2009",
  booktitle = "ADPRL 2009: Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning",
  month = "March",
  pages = "177-184",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijenadprl09.pdf",
}
@inproceedings{grappiolo:fusion09,
  title = "Integrating Distributed {B}ayesian Inference and Reinforcement Learning for Sensor Management",
  author = "Corrado Grappiolo and Shimon Whiteson and Gregor Pavlin and Bram Bakker",
  year = "2009",
  booktitle = "FUSION 2009: Proceedings of the Twelfth International Conference on Information Fusion",
  month = "July",
  pages = "93-101",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/grappiolofusion09.pdf",
}
@inproceedings{vanseijen:isda09,
  title = "Postponed Updates for Temporal-Difference Reinforcement Learning",
  author = "Harm van Seijen and Shimon Whiteson",
  year = "2009",
  booktitle = "ISDA 2009: Proceedings of the Ninth International Conference on Intelligent Systems Design and Applications",
  month = "November",
  pages = "665-672",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/vanseijenisda09.pdf",
}
@inproceedings{kroon:icmla09,
  title = "Automatic Feature Selection for Model-Based Reinforcement Learning in Factored {MDPs}",
  author = "Mark Kroon and Shimon Whiteson",
  year = "2009",
  booktitle = "ICMLA 2009: Proceedings of the Eighth International Conference on Machine Learning and Applications",
  month = "December",
  pages = "324-330",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/kroonicmla09.pdf",
}
@inproceedings{oliehoek:aamas09,
  title = "Lossless Clustering of Histories in Decentralized {POMDPs}",
  author = "Frans Oliehoek and Shimon Whiteson and Matthijs Spaan",
  year = "2009",
  booktitle = "AAMAS 2009: Proceedings of the Eighth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  pages = "577-584",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/oliehoekaamas09.pdf",
}
@techreport{ethembabaoglu:tr08,
  title = "Automatic Feature Selection using {FS-NEAT}",
  author = "Aksel Ethembabaoglu and Shimon Whiteson",
  year = "2008",
  institution = "Intelligent Autonomous Systems Group, University of Amsterdam",
  number = "IAS-UVA-08-02",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/ethembabaoglutr08.pdf",
}
@inproceedings{kuyer:ecml08,
  title = "Multiagent Reinforcement Learning for Urban Traffic Control using Coordination Graphs",
  author = "Lior Kuyer and Shimon Whiteson and Bram Bakker and Nikos Vlassis",
  year = "2008",
  booktitle = "ECML 2008: Proceedings of the Nineteenth European Conference on Machine Learning",
  month = "September",
  pages = "656-671",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/kuyerecml08.pdf",
}
@inproceedings{oliehoek:aamas08,
  title = "Exploiting Locality of Interaction in Factored {Dec-POMDPs}",
  author = "Frans Oliehoek and Matthijs Spaan and Shimon Whiteson and Nikos Vlassis",
  year = "2008",
  booktitle = "AAMAS 2008: Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  pages = "517-524",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/oliehoekaamas08.pdf",
}
@techreport{whiteson:tr07,
  title = "Adaptive Tile Coding for Value Function Approximation",
  author = "Shimon Whiteson and Matthew E. Taylor and Peter Stone",
  year = "2007",
  institution = "University of Texas at Austin",
  number = "AI-TR-07-339",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesontr07.pdf",
}
@article{whiteson:ab07,
  title = "Empirical Studies in Action Selection with Reinforcement Learning",
  author = "Shimon Whiteson and Matthew E. Taylor and Peter Stone",
  year = "2007",
  journal = "Adaptive Behavior",
  pages = "33-50",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonab07.pdf",
  volume = "15(1)",
}
@phdthesis{whiteson:thesis07,
  title = "Adaptive Representations for Reinforcement Learning",
  author = "Shimon Whiteson",
  year = "2007",
  school = "Department of Computer Science, University of Texas at Austin",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonthesis.pdf",
}
@inproceedings{taylor:aaai07,
  title = "Temporal Difference and Policy Search Methods for Reinforcement Learning: An Empirical Comparison",
  author = "Matthew E. Taylor and Shimon Whiteson and Peter Stone",
  year = "2007",
  booktitle = "AAAI 2007: Proceedings of the Twenty-Second National Conference on Artificial Intelligence",
  month = "July",
  note = "(Nectar Track)",
  pages = "1675-1678",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/tayloraaai07.pdf",
}
@inproceedings{whiteson:iaai07,
  title = "Stochastic Optimization for Collision Selection in High Energy Physics",
  author = "Shimon Whiteson and Daniel Whiteson",
  year = "2007",
  booktitle = "IAAI 2007: Proceedings of the Nineteenth Annual Innovative Applications of Artificial Intelligence Conference",
  month = "July",
  pages = "1819-1825",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesoniaai07.pdf",
}
@inproceedings{taylor:aamas07,
  title = "Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning",
  author = "Matthew E. Taylor and Shimon Whiteson and Peter Stone",
  year = "2007",
  booktitle = "AAMAS 2007: Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "May",
  pages = "156-163",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/tayloraamas07.pdf",
}
@inproceedings{whiteson:gecco06ws,
  title = "Evolutionary Function Approximation for Reinforcement Learning",
  author = "Shimon Whiteson",
  year = "2006",
  booktitle = "GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference Graduate Student Workshop",
  month = "July",
  note = "\textbf{Best Paper Award, Graduate Student Workshop}.",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesongecco06ws.pdf",
}
@inproceedings{taylor:icml06,
  title = "Transfer Learning for Policy Search Methods",
  author = "Matthew E. Taylor and Shimon Whiteson and Peter Stone",
  year = "2006",
  booktitle = "ICML 2006: Proceedings of the Twenty-Third International Conference on Machine Learning Transfer Learning Workshop",
  month = "June",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/tayloricml06.pdf",
}
@article{whiteson:jmlr06,
  title = "Evolutionary Function Approximation for Reinforcement Learning",
  author = "Shimon Whiteson and Peter Stone",
  year = "2006",
  journal = "Journal of Machine Learning Research",
  pages = "877-917",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonjmlr06.pdf",
  volume = "7",
}
@inproceedings{taylor:gecco06,
  title = "Comparing Evolutionary and Temporal Difference Methods in a Reinforcement Learning Domain",
  author = "Matthew E. Taylor and Shimon Whiteson and Peter Stone",
  year = "2006",
  booktitle = "GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  note = "\textbf{Best Paper Award, Genetic Algorithms Track}.",
  pages = "1321-1328",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/taylorgecco06.pdf",
}
@inproceedings{whiteson:gecco06,
  title = "On-Line Evolutionary Computation for Reinforcement Learning in Stochastic Domains",
  author = "Shimon Whiteson and Peter Stone",
  year = "2006",
  booktitle = "GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  pages = "1577-1584",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesongecco06.pdf",
}
@inproceedings{whiteson:aaai06,
  title = "Sample-Efficient Evolutionary Function Approximation for Reinforcement Learning",
  author = "Shimon Whiteson and Peter Stone",
  year = "2006",
  booktitle = "AAAI 2006: Proceedings of the Twenty-First National Conference on Artificial Intelligence",
  month = "July",
  pages = "518-523",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonaaai06.pdf",
}
@inproceedings{whiteson:aaai05,
  title = "Improving Reinforcement Learning Function Approximators via Neuroevolution",
  author = "Shimon Whiteson",
  year = "2005",
  booktitle = "AAAI 2005: Tenth Annual Doctoral Consortium",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonaaai05.pdf",
}
@article{whiteson:mlj05,
  title = "Evolving Keepaway Soccer Players through Task Decomposition",
  author = "Shimon Whiteson and Nate Kohl and Risto Miikkulainen and Peter Stone",
  year = "2005",
  journal = "Machine Learning",
  pages = "5-30",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonmlj05.pdf",
  volume = "59(1)",
}
@inproceedings{whiteson:gecco05,
  title = "Automatic Feature Selection in Neuroevolution",
  author = "Shimon Whiteson and Peter Stone and Kenneth O. Stanley and Risto Miikkulainen and Nate Kohl",
  year = "2005",
  booktitle = "GECCO 2005: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "June",
  pages = "1225-1232",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesongecco05.pdf",
}
@inproceedings{whiteson:gecco04,
  title = "Automatic Feature Selection in Neuroevolution",
  author = "Shimon Whiteson and Kenneth O. Stanley and Risto Miikkulainen",
  year = "2004",
  booktitle = "GECCO 2004: Proceedings of the Genetic and Evolutionary Computation Conference Workshop on Self-Organization",
  month = "July",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesongecco04.pdf",
}
@article{whiteson:eaai04,
  title = "Adaptive Job Routing and Scheduling",
  author = "Shimon Whiteson and Peter Stone",
  year = "2004",
  journal = "Engineering Applications of Artificial Intelligence",
  pages = "855-869",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesoneaai04.pdf",
  volume = "17(7)",
}
@inproceedings{whiteson:iaai04,
  title = "Towards Autonomic Computing: Adaptive Job Routing and Scheduling",
  author = "Shimon Whiteson and Peter Stone",
  year = "2004",
  booktitle = "IAAI 2004: Proceedings of the Sixteenth Annual Innovative Applications of Artificial Intelligence Conference",
  month = "July",
  pages = "916-922",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesoniaai04.pdf",
}
@inproceedings{whiteson:gecco03,
  title = "Evolving RoboCup Keepaway Players through Task Decomposition",
  author = "Shimon Whiteson and Nate Kohl and Risto Miikkulainen and Peter Stone",
  year = "2003",
  booktitle = "GECCO 2003: Proceedings of the Genetic and Evolutionary Computation Conference",
  month = "July",
  pages = "356-368",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesongecco03.pdf",
}
@inproceedings{whiteson:aamas03,
  title = "Concurrent Layered Learning",
  author = "Shimon Whiteson and Peter Stone",
  year = "2003",
  booktitle = "AAMAS 2003: Proceedings of the Second International Joint Conference on Autonomous Agents and Multi-Agent Systems",
  month = "July",
  pages = "193-200",
  url = "http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonaamas03.pdf",
}