mlsanityData to 14 Oct 2026

CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution

arXiv 2505.07854 ↗First posted 8 May 2025cs.AI cs.MAcited by 3

Not on the map. Why?

Abstract (arXiv)

Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, leading to suboptimal learning. We propose Collaborative Multi-dimensional Course Learning (CCL), a novel curriculum learning framework that addresses this by (1) refining intermediate tasks for individual agents, (2) using a variational evolutionary algorithm to generate informative subtasks, and (3) co-evolving agents with their environment to enhance training stability. Experiments on five cooperative tasks in the MPE and Hide-and-Seek environments show that CCL outperforms existing methods in sparse reward settings.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 8 May 2025.

Builds on

13 of 19 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  3. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  4. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  5. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
  6. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 259
  7. 2017One-Shot Imitation Learningcited by 233
  8. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 198
  9. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 192
  10. 2020Learning to Utilize Shaping Rewards: A New Approach of Reward Shapingcited by 114
  11. 2024CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistencycited by 7
  12. 2024Synergistic Spotting and Recognition of Micro-Expression via Temporal State Transitioncited by 6
1 more
  1. 2025Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Graph-Enhanced Policy Optimization in LLM Agent Trainingcited by 5
  2. 2026Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Designcited by 1
  3. 2026WebCryptoAgent: Agentic Crypto Trading with Web Informaticscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos
  2. 2024Collaborative Adaptation for Recovery from Unforeseen Malfunctions in Discrete and Continuous MARL Domains ↗
  3. 2025Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
  4. 2025Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
  5. 2025LLM Collaboration With Multi-Agent Reinforcement Learning
  6. 2025CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning
  7. 2026RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
  8. 2025Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage