# Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.13925 · HTML: https://mlsanity.com/paper/2505.13925/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Counterfactual Data Augmentation using Locally Factored Dynamics](https://mlsanity.com/paper/2007.02863/) (2020)
- [Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning](https://mlsanity.com/paper/1711.06782/) (2017)
- [S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning](https://mlsanity.com/paper/2103.06326/) (2021)
- [Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts](https://mlsanity.com/paper/2311.11385/) (2023)
- [Efficient Differentiable Simulation of Articulated Bodies](https://mlsanity.com/paper/2109.07719/) (2021)
- [Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications](https://mlsanity.com/paper/2408.10215/) (2024)
- [The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry](https://mlsanity.com/paper/2211.09231/) (2022)
- [A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning](https://mlsanity.com/paper/2210.04561/) (2022)
- [Recall Traces: Backtracking Models for Efficient Reinforcement Learning](https://mlsanity.com/paper/1804.00379/) (2018)
- [Forward-Backward Reinforcement Learning](https://mlsanity.com/paper/1803.10227/) (2018)
- [Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments](https://mlsanity.com/paper/1804.00361/) (2018)
- [There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning](https://mlsanity.com/paper/2106.04480/) (2021)
- [Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL](https://mlsanity.com/paper/2306.04220/) (2023)
- [Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning](https://mlsanity.com/paper/2310.18247/) (2023)
- [Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions](https://mlsanity.com/paper/2209.10656/) (2022)
- [Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates](https://mlsanity.com/paper/2310.17786/) (2023)
- [Revisiting Data Augmentation in Deep Reinforcement Learning](https://mlsanity.com/paper/2402.12181/) (2024)
- [An Investigation of Time Reversal Symmetry in Reinforcement Learning](https://mlsanity.com/paper/2311.17008/) (2023)
- [State-Novelty Guided Action Persistence in Deep Reinforcement Learning](https://mlsanity.com/paper/2409.05433/) (2024)

## Abstract (arXiv)

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.