mlsanityData to 7 Oct 2026

Emergence of Theory of Mind Collaboration in Multiagent Systems

arXiv 2110.00121 ↗First posted 30 Sep 2021cs.MA cs.AI cs.CYcited by 8

Not on the map. Why?

Abstract (arXiv)

Currently, in the study of multiagent systems, the intentions of agents are usually ignored. Nonetheless, as pointed out by Theory of Mind (ToM), people regularly reason about other's mental states, including beliefs, goals, and intentions, to obtain performance advantage in competition, cooperation or coalition. However, due to its intrinsic recursion and intractable modeling of distribution over belief, integrating ToM in multiagent planning and decision making is still a challenge. In this paper, we incorporate ToM in multiagent partially observable Markov decision process (POMDP) and propose an adaptive training algorithm to develop effective collaboration between agents with ToM. We evaluate our algorithms with two games, where our algorithm surpasses all previous decentralized execution algorithms without modeling ToM.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

25 of 40 references.

References · 25

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  3. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  4. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  5. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  6. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  7. 2016Learning Multiagent Communication with Backpropagationcited by 355
  8. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
  9. 2017Learning with Opponent-Learning Awarenesscited by 218
  10. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 181
  11. 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 180
  12. 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 123
13 more
  1. 2017Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learningcited by 114
  2. 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
  3. 2017A Survey of Learning in Multiagent Environments: Dealing with Non-Stationaritycited by 93
  4. 2017Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learningcited by 70
  5. 2019Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learningcited by 68
  6. 2018Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learningcited by 67
  7. 2017Pragmatic-Pedagogic Value Alignmentcited by 36
  8. 2018Compositional Obverter Communication Learning From Raw Visual Inputcited by 30
  9. 2018Multiagent Soft Q-Learningcited by 26
  10. 2016Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networkscited by 21
  11. 2016Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learningcited by 21
  12. 2014Monte Carlo Sampling Methods for Approximating Interactive POMDPscited by 12
  13. 2017Emergent Communication in a Multi-Modal, Multi-Step Referential Gamecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 1; 2026: 1.

8 papers.

  1. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Modelscited by 129
  2. 2024Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Informationcited by 20
  3. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  4. 2023Causal Reasoning: Charting a Revolutionary Course for Next-Generation AI-Native Wireless Networkscited by 16
  5. 2023Reasoning with the Theory of Mind for Pragmatic Semantic Communicationcited by 5
  6. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordinationcited by 3
  7. 2024Using High-Level Patterns to Estimate How Humans Predict a Robot will Behavecited by 0
  8. 2026A Primer on Computational Semantics for Artificial Intelligence Systemscited by 0