ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning
Authors:
Open Access
- 28 September 2023
- book chapter
- Published by IOS Press
- p. 2946-2953
Abstract
Multi-agent reinforcement learning (MARL) has achieved promising results in recent years. However, most existing reinforcement learning methods require a large amount of data for model training. In addition, data-efficient reinforcement learning requires the construction of strong inductive biases, which are ignored in the current MARL approaches. Inspired by the symmetry phenomenon in multi-agent systems, this paper proposes a framework for exploiting prior knowledge by integrating data augmentation and a well-designed consistency loss into the existing MARL methods. In addition, the proposed framework is model-agnostic and can be applied to most of the current MARL algorithms. Experimental tests on multiple challenging tasks demonstrate the effectiveness of the proposed framework. Moreover, the proposed framework is applied to a physical multi-robot testbed to show its superiority.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- A Comprehensive Survey of Data Augmentation in Visual Reinforcement LearningInternational Journal of Computer Vision, 2025
- A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram EstimationIEEE Transactions on Intelligent Transportation Systems, 2021
- Improving sample efficiency in Multi-Agent Actor-Critic methodsApplied Intelligence, 2021
- Decentralized Multi-Agent Pursuit Using Deep Reinforcement LearningIEEE Robotics and Automation Letters, 2021
- Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement LearningIEEE Robotics and Automation Letters, 2020
- Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenariosThe International Journal of Robotics Research, 2020
- Improving the On-Vehicle Experience of Passengers Through SC-M*: A Scalable Multi-Passenger Multi-Criteria Mobility PlannerIEEE Transactions on Intelligent Transportation Systems, 2020
- Exploiting Symmetries in Reinforcement Learning of Bimanual Robotic TasksIEEE Robotics and Automation Letters, 2019
- Emergence of Grounded Compositional Language in Multi-Agent PopulationsProceedings of the AAAI Conference on Artificial Intelligence, 2018
- A Note on Rotation MatricesIEEE Computer Graphics and Applications, 1984