Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
This addresses the problem of ambiguous reward inference in real-world applications for robotics and AI, though it is incremental as it builds on existing meta-learning and IRL techniques.
The paper tackles the challenge of inferring reward functions from limited demonstrations in inverse reinforcement learning by learning a prior over intents from other tasks, enabling efficient reward recovery from images for novel tasks.
A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly difficult to unambiguously recover a reward function. In this work, we exploit the insight that demonstrations from other tasks can be used to constrain the set of possible reward functions by learning a "prior" that is specifically optimized for the ability to infer expressive reward functions from limited numbers of demonstrations. We demonstrate that our method can efficiently recover rewards from images for novel tasks and provide intuition as to how our approach is analogous to learning a prior.