Rewriting history with inverse RL: Hindsight inference for policy improvement

Benjamin Eysenbach, Xinyang Geng, Sergey Levine, Ruslan Salakhutdinov

Research output: Contribution to journalConference articlepeer-review

26 Scopus citations

Abstract

Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency. Relabeling methods typically pose the question: if, in hindsight, we assume that our experience was optimal for some task, for what task was it optimal? Inverse RL answers this question. In this paper we show that inverse RL is a principled mechanism for reusing experience across tasks. We use this idea to generalize goal-relabeling techniques from prior work to arbitrary types of reward functions. Our experiments confirm that relabeling data using inverse RL outperforms prior relabeling methods on goal-reaching tasks, and accelerates learning on more general multi-task settings where prior methods are not applicable, such as domains with discrete sets of rewards and those with linear reward functions.

Original languageEnglish (US)
JournalAdvances in Neural Information Processing Systems
Volume2020-December
StatePublished - 2020
Externally publishedYes
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: Dec 6 2020Dec 12 2020

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Rewriting history with inverse RL: Hindsight inference for policy improvement'. Together they form a unique fingerprint.

Cite this