Skip to main content

Learning from Demonstration: Applications and challenges

Feryal Behbahani ( Latent Logic )

Recent advances in deep reinforcement learning have enabled a wide range of capabilities, from learning to play video games to acquiring robotic visuomotor skills. However, there are a wide range of problems where hand-coding behaviour or a reward function is impractical. Learning from demonstration (LfD) serves as an essential tool for learning skills that are difficult to program by hand. These demonstrations provide snapshots of near-optimal behaviours, offering guidance for the learning process and alleviating the need to start from scratch or manually engineering parts of the solution. However, it is often unclear how to acquire these in non-controlled settings, and the new challenges that arise when trying to apply these techniques in the real world.


In this talk, I will present some of the recent techniques that can help us bridge that gap and learn realistic behaviours from a large source of untapped data already existing “in the wild”. I will cover some of the latest LfD approaches that leverage recent advances in deep learning and generative adversarial methods. I will present our recent work, video to behaviour (ViBe), which can extract realistic behaviours from raw unlabelled video data, without additional expert knowledge. We can automatically extract trajectories and use them to perform LfD through a novel curriculum and cope with multiple agents interacting in complex settings. I will finish with a discussion of open questions and future research directions required to extend these approaches further.

Speaker bio

Feryal Behbahani is a Research Scientist leading the learning team at Latent Logic. Her research currently focuses on Deep Reinforcement Learning and Learning from Demonstration techniques to generate human-like behaviour that can be applied to data-driven simulators, game engines and robotics. She has worked on several projects building machine learning solutions for a variety of problems, such as robotics and videogames, as part of her PostDoc and a technology consultancy startup she co-founded. Feryal received her PhD from the Department of Computing at Imperial College London where her main research focused on investigating the underlying algorithms employed by the human brain for object representation and inference. She previously obtained her MSc in Artificial Intelligence with distinction at Imperial College London.



Share this: