Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
Abstract
Multi-goal reinforcement learning is widely applied in planning and robot manipulation. Two main challenges in multi-goal reinforcement learning are sparse rewards and sample inefficiency. Hindsight Experience Replay (HER) aims to tackle the two challenges via goal relabeling. However, HER-related works still need millions of samples and a huge computation. In this paper, we propose Multi-step Hindsight Experience Replay (MHER), incorporating multi-step relabeled returns based on -step relabeling to improve sample efficiency. Despite the advantages of -step relabeling, we theoretically and experimentally prove the off-policy -step bias introduced by -step relabeling may lead to poor performance in many environments. To address the above issue, two bias-reduced MHER algorithms, MHER() and Model-based MHER (MMHER) are presented. MHER() exploits the return while MMHER benefits from model-based value expansions. Experimental results on numerous multi-goal robotic tasks show that our solutions can successfully alleviate off-policy -step bias and achieve significantly higher sample efficiency than HER and Curriculum-guided HER with little additional computation beyond HER.
Cite
@article{arxiv.2102.12962,
title = {Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning},
author = {Rui Yang and Jiafei Lyu and Yu Yang and Jiangpeng Yan and Feng Luo and Dijun Luo and Lanqing Li and Xiu Li},
journal= {arXiv preprint arXiv:2102.12962},
year = {2022}
}
Comments
20pages, 8 figures