mlsanityData to 7 Oct 2026

Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning

arXiv 2006.07169 ↗First posted 12 Jun 2020cs.MA cs.LGcited by 114

Not on the map. Why?

Abstract (arXiv)

Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called Shared Experience Actor-Critic (SEAC), applies experience sharing in an actor-critic framework. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms two baselines and two state-of-the-art algorithms by learning in fewer steps and converging to higher returns. In some harder environments, experience sharing makes the difference between learning to solve the task and not learning at all.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 22; 2023: 25; 2024: 14; 2025: 33; 2026: 10.

114 papers.

Sort:

By area:

  1. 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 96
  2. 2021Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharingcited by 85
  3. 2023JaxMARL: Multi-Agent RL Environments and Algorithms in JAXcited by 59
  4. 2021Cooperative Exploration for Multi-Agent Deep Reinforcement Learningcited by 57
  5. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 48
  6. 2022MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffercited by 34
  7. 2022Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learningcited by 32
  8. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 30
  9. 2022Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workerscited by 28
  10. 2023A Review of Cooperation in Multi-agent Learningcited by 27
  11. 2021Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Explorationcited by 25
  12. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithmscited by 23
38 more
  1. 2022MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Librarycited by 21
  2. 2023Distributed Control of Partial Differential Equations Using Convolutional Reinforcement Learningcited by 21
  3. 2024POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfindingcited by 20
  4. 2025Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignmentcited by 17
  5. 2021Mava: a research library for distributed multi-agent reinforcement learning in JAXcited by 14
  6. 2022Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learningcited by 14
  7. 2023Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agentscited by 13
  8. 2022Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learningcited by 12
  9. 2023Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learningcited by 12
  10. 2022Toward Policy Explanations for Multi-Agent Reinforcement Learningcited by 11
  11. 2022Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENScited by 10
  12. 2024Sable: a Performant, Efficient and Scalable Sequence Model for MARLcited by 10
  13. 2024HyperMARL: Adaptive Hypernetworks for Multi-Agent RLcited by 10
  14. 2021LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammatescited by 9
  15. 2023Explainable Multi-Agent Reinforcement Learning for Temporal Queriescited by 9
  16. 2023IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARLcited by 9
  17. 2023Learning Multi-Agent Communication with Contrastive Learningcited by 9
  18. 2024Multi-Sender Persuasion: A Computational Perspectivecited by 9
  19. 2021Learning Altruistic Behaviours in Reinforcement Learning without External Rewardscited by 8
  20. 2022Federated Reinforcement Learning for Collective Navigation of Robotic Swarmscited by 7
  21. 2023Self-Motivated Multi-Agent Explorationcited by 7
  22. 2022Trust-based Consensus in Multi-Agent Reinforcement Learning Systemscited by 6
  23. 2025ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamworkcited by 6
  24. 2022Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learningcited by 5
  25. 2022Learning Latent Representations to Co-Adapt to Humanscited by 5
  26. 2023Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learningcited by 5
  27. 2024The Bandit Whisperer: Communication Learning for Restless Banditscited by 5
  28. 2023Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learningcited by 4
  29. 2023Efficiently Quantifying Individual Agent Importance in Cooperative MARLcited by 4
  30. 2024Putting Data at the Centre of Offline Multi-Agent Reinforcement Learningcited by 4
  31. 2025Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learningcited by 4
  32. 2022The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applicationscited by 3
  33. 2022Logic-based Reward Shaping for Multi-Agent Reinforcement Learningcited by 3
  34. 2022Deep Reinforcement Learning for Multi-Agent Interactioncited by 3
  35. 2023VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Modelcited by 3
  36. 2023Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learningcited by 3
  37. 2024Revisiting Experience Replayable Conditionscited by 3
  38. 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Explorationcited by 3

50 most cited of 114 All 114 (JSON)