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 $n$-step relabeling to improve sample efficiency. Despite the advantages of $n$-step relabeling, we theoretically and experimentally prove the off-policy $n$-step bias introduced by $n$-step relabeling may lead to poor performance in many environments. To address the above issue, two bias-reduced MHER algorithms, MHER($\lambda$) and Model-based MHER (MMHER) are presented. MHER($\lambda$) exploits the $\lambda$ 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 $n$-step bias and achieve significantly higher sample efficiency than HER and Curriculum-guided HER with little additional computation beyond HER.

arXiv comment20pages, 8 figures

References in corpus (9)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
• Distributed Distributional Deterministic Policy Gradients
• Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
• Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
• Sharing Knowledge in Multi-Task Deep Reinforcement Learning
• Maximum Entropy-Regularized Multi-Goal Reinforcement Learning

Cited by in corpus (1)

• Conservative Data Sharing for Multi-Task Offline Reinforcement Learning