mlsanityData to 14 Oct 2026

ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning

arXiv 2307.16186 ↗First posted 30 Jul 2023cs.MA cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 30 Jul 2023.

Builds on

29 of 47 references.

References · 29

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  3. 2016Group Equivariant Convolutional Networkscited by 1,165
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  5. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  6. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  7. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  8. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  9. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 585
  10. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  11. 2020Reinforcement Learning with Augmented Datacited by 468
  12. 2016Steerable CNNscited by 305
17 more
  1. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  2. 2020"Other-Play" for Zero-Shot Coordinationcited by 198
  3. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
  4. 2018Graph Convolutional Reinforcement Learningcited by 152
  5. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 142
  6. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  7. 2019Scale-Equivariant Steerable Networkscited by 110
  8. 2021Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharingcited by 87
  9. 2022SO(2)-Equivariant Reinforcement Learningcited by 84
  10. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 82
  11. 2020Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learningcited by 48
  12. 2021A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimationcited by 37
  13. 2021Multi-Agent MDP Homomorphic Networkscited by 25
  14. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 25
  15. 2020Decentralized Multi-Agent Pursuit using Deep Reinforcement Learningcited by 23
  16. 2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21
  17. 2021Implicit Equivariance in Convolutional Networkscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 5; 2026: 2.

9 papers.

  1. 2024Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Taskscited by 13
  2. 2023rm E(3)-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learningcited by 6
  3. 2025SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfindingcited by 4
  4. 2025Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategiescited by 1
  5. 2025Solving the Min-Max Multiple Traveling Salesmen Problem via Learning-Based Path Generation and Optimal Splittingcited by 1
  6. 2026Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systemscited by 1
  7. 2025Symmetry-Guided Multi-Agent Inverse Reinforcement Learningcited by 0
  8. 2025Reinforcement Learning Using known Invariancescited by 0
  9. 2026Episodic Memory Temporal Consistency for Cooperative Multi-Agent Reinforcement Learningcited by 0