mlsanityData to 14 Oct 2026

GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning

arXiv 2606.25073 ↗First posted 23 Jun 2026cs.LG cs.AI cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task. In this work, we propose GCT-MARL, a transfer learning framework that builds on the multi-view graph contrastive backbone of MAIL and augments it with a per-view, adaptively weighted alignment loss and a two-phase training protocol specifically designed for transfer across populations of varying sizes and compositions. We empirically demonstrate that the proposed framework markedly accelerates convergence on the target task relative to from-scratch training, in both homogeneous (within-faction, varying N) and heterogeneous (cross-faction and mixed unit-type) transfer scenarios. Furthermore, we show that the framework naturally supports continual learning by sequentially chaining the two-phase transfer protocol across a series of related tasks. Overall, this work provides a unified approach to mitigating key limitations in current MARL transfer methods with new insights at both methodological and empirical levels.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

24 of 41 references.

References · 24

  1. 2017Graph Attention Networkscited by 8,923
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2016Learning without Forgettingcited by 2,496
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  6. 2018Deep Graph Infomaxcited by 1,106
  7. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  8. 2019The StarCraft Multi-Agent Challengecited by 597
  9. 2018Progress & Compress: A scalable framework for continual learningcited by 520
  10. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  11. 2015Policy Distillationcited by 440
  12. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
12 more
  1. 2016Learning Multiagent Communication with Backpropagationcited by 366
  2. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
  3. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  4. 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
  5. 2018Graph Convolutional Reinforcement Learningcited by 152
  6. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 82
  7. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  8. 2020Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learningcited by 48
  9. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  10. 2020Learning Structured Communication for Multi-agent Reinforcement Learningcited by 21
  11. 2019Autonomous Air Traffic Controller: A Deep Multi-Agent Reinforcement Learning Approachcited by 10
  12. 2024MARLens: Understanding Multi-agent Reinforcement Learning for Traffic Signal Control via Visual Analyticscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations
  2. 2026ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
  3. 2024Multi-Agent Transfer Learning via Temporal Contrastive Learning
  4. 2026Graphon Mean-Field Subsampling for Cooperative Heterogeneous Multi-Agent Reinforcement Learning
  5. 2025An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks
  6. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  7. 2024Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks
  8. 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy