Postdoctoral Researcher in Reinforcement Learning (fixed term)

Fixed term for 2 years from 1 October 2015, or as soon as possible thereafter
Grade 7: Salary £30,434 – £37,394 p.a.

An opening for a full-time Postdoctoral Researcher in Reinforcement Learning has arisen in the Department of Computer Science. The aim of this project is to develop a new class of reinforcement learning and sample-based decision-theoretic planning methods that overcome fundamental obstacles to the efficient optimisation of control policies for autonomous agents. 

Reporting to Professor Shimon Whiteson, the focus will be on policy-search methods for reinforcement learning, and techniques such as stochastic optimisation, Bayesian optimisation, and Bayesian quadrature are expected to play a key role. It offers an interesting balance of both theoretical work, as well as an extensive empirical analysis on challenging tasks from robotics and information retrieval.

You should have a PhD in Computer Science or related area (or be very close to completion), with good knowledge of the current state-of-the-art in machine learning, evidenced by a track record of research in the areas of machine learning or decision-theoretic planning (or a related area). Experience of conducting large-scale experiments with large-scale datasets and knowledge of the current state-of-the-art in reinforcement learning and decision-theoretic planning are highly desirable.

The closing date for applications is 12 noon on 29 July 2015.

For further details and to apply please visit: https://www.recruit.ox.ac.uk/pls/hrisliverecruit/erq_jobspec_version_4.jobspec?p_id=119004