Soft Hindsight Experience Replay

Abstract

Efficient learning in the environment with sparse rewards is one of the most important challenges in Deep Reinforcement Learning (DRL). In continuous DRL environments such as robotic arms control, Hindsight Experience Replay (HER) has been shown an effective solution. However, due to the brittleness of deterministic methods, HER and its variants typically suffer from a major challenge for stability and convergence, which significantly affects the final performance. This challenge severely limits the applicability of such methods to complex real-world domains. To tackle this challenge, in this paper, we propose Soft Hindsight Experience Replay (SHER), a novel approach based on HER and Maximum Entropy Reinforcement Learning (MERL), combining the failed experiences reuse and maximum entropy probabilistic inference model. We evaluate SHER on Open AI Robotic manipulation tasks with sparse rewards. Experimental results show that, in contrast to HER and its variants, our proposed SHER achieves state-of-the-art performance, especially in the difficult HandManipulation tasks. Furthermore, our SHER method is more stable, achieving very similar performance across different random seeds.

7 pages, 5 figures, 1 table, submitted to IJCAI2020

References in corpus (11)

• Continuous control with deep reinforcement learning
• Playing Atari with Deep Reinforcement Learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• Learning Dexterous In-Hand Manipulation
• Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
• Equivalence Between Policy Gradients and Soft Q-Learning
• Curiosity-Driven Experience Prioritization via Density Estimation
• If MaxEnt RL is the Answer, What is the Question?
• Energy-Based Hindsight Experience Prioritization

Cited by in corpus (4)

• PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals
• Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning
• Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks
• Self-Imitation Learning for Robot Tasks with Sparse and Delayed Rewards