Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
arXiv:1805.12573
Abstract
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.
References in corpus (12)
- Prototypical Networks for Few-shot Learning
- Recurrent Neural Network Regularization
- Theoretical Models of Learning to Learn
- Learning to reinforcement learn
- Maximum Entropy Deep Inverse Reinforcement Learning
- TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
- Bayesian multitask inverse reinforcement learning
- Learning to Optimize Neural Nets
- Attentive Recurrent Comparators
- From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
- Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
- Meta Inverse Reinforcement Learning via Maximum Reward Sharing for Human Motion Analysis