Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards

2024/03/27 by Yasin Sönmez, Neelay Junnarkar, Sonmez, Yasin +3
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2403.19024

openalex publication_date 2024/03/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry; however, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model. In this paper, we assume only the dynamics exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory to which symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics that, by construction, exhibit specified symmetries. Numerical experiments demonstrate that the proposed method learns a more accurate dynamical model

Related

• Symmetry Learning for Function Approximation in Reinforcement Learning
• Reinforcement Learning Using known Invariances
• Augmenting learning using symmetry in a biologically-inspired domain
• Sample Efficient Dynamics Learning for Symmetrical Legged Robots:Leveraging Physics Invariance and Geometric Symmetries
• Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations