mlsanityData to 14 Oct 2026

Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning

arXiv 2505.13925 ↗First posted 20 May 2025cs.RO cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

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.

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.

Builds on

25 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Revisiting Data Augmentation in Deep Reinforcement Learning19 Feb

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  4. 2016Group Equivariant Convolutional Networkscited by 1,165
  5. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  6. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 372
  7. 2020Counterfactual Data Augmentation using Locally Factored Dynamicscited by 93
  8. 2017Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learningcited by 90
  9. 2021S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningcited by 85
  10. 2023Multi-Task Reinforcement Learning with Mixture of Orthogonal Expertscited by 49
  11. 2021Efficient Differentiable Simulation of Articulated Bodiescited by 39
  12. 2024Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applicationscited by 38
12 more
  1. 2022The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetrycited by 33
  2. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 25
  3. 2018Recall Traces: Backtracking Models for Efficient Reinforcement Learningcited by 23
  4. 2018Forward-Backward Reinforcement Learningcited by 19
  5. 2018Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environmentscited by 19
  6. 2021There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learningcited by 18
  7. 2023Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RLcited by 18
  8. 2023Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learningcited by 10
  9. 2022Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructionscited by 8
  10. 2023Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updatescited by 7
  11. 2023An Investigation of Time Reversal Symmetry in Reinforcement Learningcited by 1
  12. 2024State-Novelty Guided Action Persistence in Deep Reinforcement Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Symmetry Considerations for Learning Task Symmetric Robot Policies
  2. 2025Symmetry-Guided Multi-Agent Inverse Reinforcement Learning
  3. 2026Sample Complexity of Equivariant Reinforcement Learning
  4. 2026RESTA: Time-Scaling Augmentation for Data-Efficient Robot Imitation Learning
  5. 2024Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards
  6. 2025Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation
  7. 2024Leveraging Symmetry in RL-based Legged Locomotion Control
  8. 2025Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy