Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control
Abstract
Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decision Processes (-invariant MDPs). Existing works in this direction have primarily focused on image-based RL and rotational symmetry such as , leaving state-based RL and reflection symmetry largely underexplored. In this work, we focus on state-based continuous control tasks and exploit reflection symmetry by introducing Reflex, a paradigm that seamlessly integrates with both on-policy and off-policy RL algorithms. We formalize two types of reflection-axial reflection and bilateral reflection, and characterize their corresponding transformations. Building on a theoretical analysis of symmetry-preserving optimal value functions and policies, Reflex integrates reflection symmetry into policy learning through principled symmetry regularization mechanisms. We integrate Reflex with PPO and SAC, and evaluate it on a suite of OpenAI Gym and DeepMind Control benchmarks, demonstrating superior performance over standard baselines while improving sample efficiency. Our code is available at https://github.com/TonyStark042/Reflex.
Cite
@article{arxiv.2605.23415,
title = {Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control},
author = {Shuai Zhen and Yifan Zhang and Yuling Wang and Yanhua Yu},
journal= {arXiv preprint arXiv:2605.23415},
year = {2026}
}