mlsanityData to 14 Oct 2026

Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments

arXiv 2209.10958 ↗First posted 22 Sep 2022cs.MA cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks. A signature aim of our group is to use the resources and expertise made available to us at DeepMind in deep reinforcement learning to explore multi-agent systems in complex environments and use these benchmarks to advance our understanding. Here, we summarise the recent work of our team and present a taxonomy that we feel highlights many important open challenges in multi-agent research.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 63 of its 98 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

63 of 98 references.

References · 63

  1. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  2. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  3. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 268
  4. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  5. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 186
  6. 2020Open Problems in Cooperative AIcited by 168
  7. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 158
  8. 2021Collaborating with Humans without Human Datacited by 142
  9. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  10. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 99
  11. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  12. 2017A multi-agent reinforcement learning model of common-pool resource appropriationcited by 69
38 more
  1. 2020Real World Games Look Like Spinning Topscited by 66
  2. 2020Fictitious Play for Mean Field Games: Continuous Time Analysis and Applicationscited by 62
  3. 2019Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researchcited by 61
  4. 2020From Poincar'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularizationcited by 61
  5. 2019Emergent Coordination Through Competitioncited by 57
  6. 2020Learning to Incentivize Other Learning Agentscited by 57
  7. 2021Concave Utility Reinforcement Learning: the Mean-Field Game Viewpointcited by 56
  8. 2019A Generalized Training Approach for Multiagent Learningcited by 54
  9. 2019α-Rank: Multi-Agent Evaluation by Evolutioncited by 51
  10. 2020Social diversity and social preferences in mixed-motive reinforcement learningcited by 49
  11. 2019On the Convergence of Model Free Learning in Mean Field Gamescited by 48
  12. 2019Biases for Emergent Communication in Multi-agent Reinforcement Learningcited by 48
  13. 2018Re-evaluating Evaluationcited by 47
  14. 2020Human-Level Performance in No-Press Diplomacy via Equilibrium Searchcited by 41
  15. 2020EigenGame: PCA as a Nash Equilibriumcited by 39
  16. 2019No Press Diplomacy: Modeling Multi-Agent Gameplaycited by 38
  17. 2022Scalable Deep Reinforcement Learning Algorithms for Mean Field Gamescited by 38
  18. 2018Actor-Critic Policy Optimization in Partially Observable Multiagent Environmentscited by 35
  19. 2021Scaling up Mean Field Games with Online Mirror Descentcited by 32
  20. 2019Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descentcited by 31
  21. 2021Mean Field Games Flock! The Reinforcement Learning Waycited by 31
  22. 2021No-Press Diplomacy from Scratchcited by 31
  23. 2018Evolving intrinsic motivations for altruistic behaviorcited by 30
  24. 2021Generalization in Mean Field Games by Learning Master Policiescited by 28
  25. 2020Game Plan: What AI can do for Football, and What Football can do for AIcited by 27
  26. 2020Learning to Play No-Press Diplomacy with Best Response Policy Iterationcited by 26
  27. 2021A learning agent that acquires social norms from public sanctions in decentralized multi-agent settingscited by 24
  28. 2022On the role of population heterogeneity in emergent communicationcited by 24
  29. 2021Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solverscited by 21
  30. 2021Neural Recursive Belief States in Multi-Agent Reinforcement Learningcited by 18
  31. 2020The Advantage Regret-Matching Actor-Criticcited by 17
  32. 2020D3C: Reducing the Price of Anarchy in Multi-Agent Learningcited by 16
  33. 2018Malthusian Reinforcement Learningcited by 14
  34. 2021Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSROcited by 14
  35. 2022NeuPL: Neural Population Learningcited by 14
  36. 2019Neural Replicator Dynamicscited by 13
  37. 2020Negotiating Team Formation Using Deep Reinforcement Learningcited by 13
  38. 2021EigenGame Unloaded: When playing games is better than optimizingcited by 13

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023Online Learning and Solving Infinite Games with an ERM Oraclecited by 11
  2. 2025The Hidden Game Problemcited by 0