USHER: Unbiased Sampling for Hindsight Experience ReplayDownload PDF

Published: 10 Sept 2022, Last Modified: 12 Mar 2024CoRL 2022 PosterReaders: Everyone
Keywords: Reinforcement Learning, Multi-goal reinforcement learning, Reinforcement learning theory
TL;DR: We derive a provably unbiased variant of Hindsight Experience Replay without sacrificing HER's low variance or high sample efficiency.
Abstract: Dealing with sparse rewards is a long-standing challenge in reinforcement learning (RL). Hindsight Experience Replay (HER) addresses this problem by reusing failed trajectories for one goal as successful trajectories for another. This allows for both a minimum density of reward and for generalization across multiple goals. However, this strategy is known to result in a biased value function, as the update rule underestimates the likelihood of bad outcomes in a stochastic environment. We propose an asymptotically unbiased importance-sampling-based algorithm to address this problem without sacrificing performance on deterministic environments. We show its effectiveness on a range of robotic systems, including challenging high dimensional stochastic environments.
Student First Author: yes
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
10 Replies