Bayesian Robust Optimization for Imitation Learning

arXiv:2007.12315v4 Announce Type: replace
Abstract: One of the main challenges in imitation learning is determining what action an agent should take when outside the state distribution of the demonstrations. Inverse reinforcement learning (IRL) can enable generalization to new states by learning a parameterized reward function, but these approaches still face uncertainty over the true reward function and corresponding optimal policy. Existing safe imitation learning approaches based on IRL deal with this uncertainty using a maxmin framework that optimizes a policy …

arxiv bayesian cs.lg imitation learning optimization robust stat.ml type