mlsanityData to 7 Oct 2026

Modeling Others using Oneself in Multi-Agent Reinforcement Learning

arXiv 1802.09640 ↗First posted 26 Feb 2018cs.AI cs.LGcited by 64

Not on the map. Why?

Abstract (arXiv)

We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players' hidden states, in both cooperative and adversarial settings.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 10; 2023: 9; 2024: 8; 2025: 12; 2026: 7.

64 papers.

Sort:

By area:

  1. 2023Understanding Social Reasoning in Language Models with Language Modelscited by 166
  2. 2023MADiff: Offline Multi-agent Learning with Diffusion Modelscited by 73
  3. 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 65
  4. 2021Cooperative Exploration for Multi-Agent Deep Reinforcement Learningcited by 57
  5. 2021ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mindcited by 57
  6. 2022Model-Free Opponent Shapingcited by 43
  7. 2021Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of otherscited by 39
  8. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 30
  9. 2021Model-Based Opponent Modelingcited by 21
  10. 2021CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Modelscited by 20
  11. 2021Collaborative Visual Navigationcited by 18
  12. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
38 more
  1. 2022Influencing Long-Term Behavior in Multiagent Reinforcement Learningcited by 18
  2. 2025Virtual Agent Economiescited by 17
  3. 2021Co-GAIL: Learning Diverse Strategies for Human-Robot Collaborationcited by 16
  4. 2021Causal Multi-Agent Reinforcement Learning: Review and Open Problemscited by 16
  5. 2022Multi-Agent Coordination via Multi-Level Communicationcited by 14
  6. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  7. 2021Joint Attention for Multi-Agent Coordination and Social Learningcited by 8
  8. 2022Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Gamescited by 8
  9. 2023Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Financecited by 7
  10. 2024Fast Peer Adaptation with Context-aware Explorationcited by 7
  11. 2022CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spacescited by 6
  12. 2024Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Gamescited by 6
  13. 2024Towards Safe and Honest AI Agents with Neural Self-Other Overlapcited by 6
  14. 2021Dealing with Non-Stationarity in MARL via Trust-Region Decompositioncited by 5
  15. 2022Learning Latent Representations to Co-Adapt to Humanscited by 5
  16. 2023Learning Models of Adversarial Agent Behavior under Partial Observabilitycited by 5
  17. 2024On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flowcited by 5
  18. 2021Multi-Agent Advisor Q-Learningcited by 4
  19. 2024Predicting Future Actions of Reinforcement Learning Agentscited by 4
  20. 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)cited by 4
  21. 2023Decentralized Multi-Agent Reinforcement Learning with Global State Predictioncited by 3
  22. 2024Informativeness of Reward Functions in Reinforcement Learningcited by 3
  23. 2024Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactionscited by 3
  24. 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Explorationcited by 3
  25. 2025Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Modelscited by 3
  26. 2021A Bayesian Approach to Identifying Representational Errorscited by 2
  27. 2021Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learningcited by 2
  28. 2022Decision-making with Speculative Opponent Modelscited by 2
  29. 2023Diffusion Models for Multi-target Adversarial Trackingcited by 2
  30. 2024Scalable Interactive Machine Learning for Future Command and Controlcited by 2
  31. 2025Trajectory-Class-Aware Multi-Agent Reinforcement Learningcited by 2
  32. 2025Strategy-Augmented Planning for Large Language Models via Opponent Exploitationcited by 2
  33. 2021Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Coloniescited by 1
  34. 2021Metric Policy Representations for Opponent Modelingcited by 1
  35. 2022Safe adaptation in multiagent competitioncited by 1
  36. 2023EMOTE: An Explainable architecture for Modelling the Other Through Empathycited by 1
  37. 2025Modeling Latent Partner Strategies for Adaptive Zero-Shot Human-Agent Collaborationcited by 1
  38. 2025TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encodingcited by 1

50 most cited of 64 All 64 (JSON)