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

• Type: Article in International Scientific Journal
• Date: 2025

Authors

Abreu, M (Author) Other; reis, lp (Author) FEUP; Lau, N (Author) Other

Journal

Title: Neurocomputing

Vol. 614

ISSN: 0925-2312

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-00Z-258

DOI: 10.1016/j.neucom.2024.128771

Abstract (EN): 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 asymmetry 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 inmost scenarios, making it a valuable approach for leveraging model symmetry while compensating for inherent perturbations.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 31