mlsanityData to 14 Oct 2026

Learning Multi-Robot Coordination through Locality-Based Factorized Multi-Agent Actor-Critic Algorithm

arXiv 2503.18816 ↗First posted 24 Mar 2025cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work, we present a novel cooperative multi-agent reinforcement learning method called Locality based Factorized Multi-Agent Actor-Critic (Loc-FACMAC). Existing state-of-the-art algorithms, such as FACMAC, rely on global reward information, which may not accurately reflect the quality of individual robots' actions in decentralized systems. We integrate the concept of locality into critic learning, where strongly related robots form partitions during training. Robots within the same partition have a greater impact on each other, leading to more precise policy evaluation. Additionally, we construct a dependency graph to capture the relationships between robots, facilitating the partitioning process. This approach mitigates the curse of dimensionality and prevents robots from using irrelevant information. Our method improves existing algorithms by focusing on local rewards and leveraging partition-based learning to enhance training efficiency and performance. We evaluate the performance of Loc-FACMAC in three environments: Hallway, Multi-cartpole, and Bounded-Cooperative-Navigation. We explore the impact of partition sizes on the performance and compare the result with baseline MARL algorithms such as LOMAQ, FACMAC, and QMIX. The experiments reveal that, if the locality structure is defined properly, Loc-FACMAC outperforms these baseline algorithms up to 108%, indicating that exploiting the locality structure in the actor-critic framework improves the MARL performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

23 of 33 references.

References · 23

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  3. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  4. 2019The StarCraft Multi-Agent Challengecited by 597
  5. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  6. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
  7. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  8. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  9. 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
  10. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
  11. 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 116
  12. 2019Deep Coordination Graphscited by 98
11 more
  1. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 82
  2. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  3. 2020R-MADDPG for Partially Observable Environments and Limited Communicationcited by 36
  4. 2021Context-Aware Sparse Deep Coordination Graphscited by 28
  5. 2022AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-Ncited by 22
  6. 2022QGNN: Value Function Factorisation with Graph Neural Networkscited by 14
  7. 2022Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Methodcited by 10
  8. 2021MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learningcited by 6
  9. 2022Traversing Supervisor Problem: An Approximately Optimal Approach to Multi-Robot Assistancecited by 4
  10. 2021Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learningcited by 3
  11. 2023Coordination and Machine Learning in Multi-Robot Systems: Applications in Robotic Soccercited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Bi-CL: A Reinforcement Learning Framework for Robots Coordination Through Bi-level Optimization
  2. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  3. 2024Graph Neural Network-based Multi-agent Reinforcement Learning for Resilient Distributed Coordination of Multi-Robot Systems
  4. 2026Coordination Graphs for Constrained Multi-Agent Reinforcement Learning
  5. 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy
  6. 2026Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
  7. 2025A Communication-Efficient Decentralized Actor-Critic Algorithm
  8. 2026HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization