Inverse Reinforcement Learning infers a reward function from expert demonstrations, aiming to encode the behavior and intentions of the expert. Current approaches usually do this with generative and uni-modal models, meaning that they encode a single behavior. In the common setting, where there are various solutions to a problem and the experts show versatile behavior this severely limits the generalization capabilities of these methods. We propose a novel method for Inverse Reinforcement Learning that overcomes these problems by formulating the recovered reward as a sum of iteratively trained discriminators. We show on simulated tasks that our approach is able to recover general, high-quality reward functions and produces policies of the same quality as behavioral cloning approaches designed for versatile behavior.
@article{arxiv.2111.07667,
title = {Versatile Inverse Reinforcement Learning via Cumulative Rewards},
author = {Niklas Freymuth and Philipp Becker and Gerhard Neumann},
journal= {arXiv preprint arXiv:2111.07667},
year = {2021}
}
Comments
Accepted as a workshop paper in 4th Robot Learning Workshop: Self-Supervised and Lifelong Learning @NeurIPS 2021