Addressing imperfect symmetry: A novel symmetry-learning actor-critic extension
This work addresses the challenge of leveraging symmetry in reinforcement learning for robotics or control systems where perfect symmetry assumptions fail, though it appears incremental as an extension to existing actor-critic methods.
The paper tackled the problem of imperfect symmetry in reinforcement learning by introducing Adaptive Symmetry Learning (ASL), an actor-critic extension that adapts to incomplete symmetry descriptions during learning, achieving comparable or better performance than existing methods in multidirectional locomotion tasks with a four-legged ant model.
Symmetry, a fundamental concept to understand our environment, often oversimplifies reality from a mathematical perspective. Humans are a prime example, deviating from perfect symmetry in terms of appearance and cognitive biases (e.g. having a dominant hand). Nevertheless, our brain can easily overcome these imperfections and efficiently adapt to symmetrical tasks. The driving motivation behind this work lies in capturing this ability through reinforcement learning. To this end, we introduce Adaptive Symmetry Learning (ASL), a model-minimization actor-critic extension that addresses incomplete or inexact symmetry descriptions by adapting itself during the learning process. ASL consists of a symmetry fitting component and a modular loss function that enforces a common symmetric relation across all states while adapting to the learned policy. The performance of ASL is compared to existing symmetry-enhanced methods in a case study involving a four-legged ant model for multidirectional locomotion tasks. The results show that ASL can recover from large perturbations and generalize knowledge to hidden symmetric states. It achieves comparable or better performance than alternative methods in most scenarios, making it a valuable approach for leveraging model symmetry while compensating for inherent perturbations.