Addressing imperfect symmetry: A novel symmetry-learning actor-critic extension

TL;DR

This paper introduces Adaptive Symmetry Learning (ASL), a reinforcement learning extension that effectively captures imperfect symmetry, adapts during learning, and improves performance in symmetric tasks like quadruped locomotion.

Contribution

The paper proposes a novel symmetry-learning actor-critic extension that adapts to incomplete symmetry descriptions during training, enhancing generalization and robustness.

Findings

ASL recovers from large perturbations in symmetry.

ASL outperforms existing methods in most scenarios.

ASL generalizes to hidden symmetric states.

Abstract

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.