A Bayesian Approach to Robust Inverse Reinforcement Learning

arXiv:2309.08571v2 Announce Type: replace
Abstract: We consider a Bayesian approach to offline model-based inverse reinforcement learning (IRL). The proposed framework differs from existing offline model-based IRL approaches by performing simultaneous estimation of the expert's reward function and subjective model of environment dynamics. We make use of a class of prior distributions which parameterizes how accurate the expert's model of the environment is to develop efficient algorithms to estimate the expert's reward and subjective dynamics in high-dimensional settings. Our analysis reveals …

abstract arxiv bayesian class cs.lg dynamics environment expert framework function offline prior reinforcement reinforcement learning robust type