Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning

TL;DR

This paper introduces TR-DRL, a novel framework leveraging time reversal symmetry in robotics to enhance deep reinforcement learning by augmenting data and shaping rewards, leading to improved efficiency and performance.

Contribution

The paper pioneers the use of time reversal symmetry in DRL, combining trajectory reversal and reward shaping to better learn temporally symmetric tasks.

Findings

TR-DRL outperforms baseline methods in sample efficiency.

TR-DRL achieves higher final performance on benchmarks.

Effective in both single-task and multi-task settings.

Abstract

Symmetry is pervasive in robotics and has been widely exploited to improve sample efficiency in deep reinforcement learning (DRL). However, existing approaches primarily focus on spatial symmetries, such as reflection, rotation, and translation, while largely neglecting temporal symmetries. To address this gap, we explore time reversal symmetry, a form of temporal symmetry commonly found in robotics tasks such as door opening and closing. We propose Time Reversal symmetry enhanced Deep Reinforcement Learning (TR-DRL), a framework that combines trajectory reversal augmentation and time reversal guided reward shaping to efficiently solve temporally symmetric tasks. Our method generates reversed transitions from fully reversible transitions, identified by a proposed dynamics-consistent filter, to augment the training data. For partially reversible transitions, we apply reward shaping to guide learning, according to successful trajectories from the reversed task. Extensive experiments on the Robosuite and MetaWorld benchmarks demonstrate that TR-DRL is effective in both single-task and multi-task settings, achieving higher sample efficiency and stronger final performance compared to baseline methods.