English

Versatile Inverse Reinforcement Learning via Cumulative Rewards

Machine Learning 2021-11-16 v1

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-24T07:38:35.085Z