mlsanityData to 7 Oct 2026

Agent Modelling under Partial Observability for Deep Reinforcement Learning

arXiv 2006.09447 ↗First posted 16 Jun 2020cs.LG cs.MA stat.MLcited by 56

Not on the map. Why?

Abstract (arXiv)

Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from the local information of the controlled agent using encoder-decoder architectures. Using the observations and actions of the modelled agents during training, our models learn to extract representations about the modelled agents conditioned only on the local observations of the controlled agent. The representations are used to augment the controlled agent's decision policy which is trained via deep reinforcement learning; thus, during execution, the policy does not require access to other agents' information. We provide a comprehensive evaluation and ablations studies in cooperative, competitive and mixed multi-agent environments, showing that our method achieves higher returns than baseline methods which do not use the learned representations.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 13; 2024: 7; 2025: 14; 2026: 14.

56 papers.

Sort:

By area:

  1. 2023MADiff: Offline Multi-agent Learning with Diffusion Modelscited by 73
  2. 2024Learning to Cooperate with Humans using Generative Agentscited by 23
  3. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  4. 2022Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversitycited by 17
  5. 2024N-Agent Ad Hoc Teamworkcited by 15
  6. 2023Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agentscited by 13
  7. 2022A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 12
  8. 2023Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimationcited by 10
  9. 2024Fast Peer Adaptation with Context-aware Explorationcited by 7
  10. 2024SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systemscited by 7
  11. 2022Verified Probabilistic Policies for Deep Reinforcement Learningcited by 6
  12. 2024Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowdscited by 6
38 more
  1. 2025ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamworkcited by 6
  2. 2022Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learningcited by 5
  3. 2023iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learningcited by 5
  4. 2023Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learningcited by 4
  5. 2024Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learningcited by 4
  6. 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)cited by 4
  7. 2026TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systemscited by 4
  8. 2022Deep Reinforcement Learning for Multi-Agent Interactioncited by 3
  9. 2023CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learningcited by 3
  10. 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Explorationcited by 3
  11. 2022Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learningcited by 2
  12. 2022Decision-making with Speculative Opponent Modelscited by 2
  13. 2023Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement Learningcited by 2
  14. 2023Contrastive learning-based agent modeling for deep reinforcement learningcited by 2
  15. 2025Trajectory-Class-Aware Multi-Agent Reinforcement Learningcited by 2
  16. 2023EMOTE: An Explainable architecture for Modelling the Other Through Empathycited by 1
  17. 2023Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learningcited by 1
  18. 2023Fact-based Agent modeling for Multi-Agent Reinforcement Learningcited by 1
  19. 2025Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observabilitycited by 1
  20. 2025From Grunts to Lexicons: Emergent Language from Cooperative Foragingcited by 1
  21. 2025TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encodingcited by 1
  22. 2026Multi-Agent Systems Should be Treated as Principal-Agent Problemscited by 1
  23. 2026Belief Dynamics for Detecting Behavioral Shifts in Safe Collaborative Manipulationcited by 1
  24. 2023Latent Interactive A2C for Improved RL in Open Many-Agent Systemscited by 0
  25. 2023Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interactioncited by 0
  26. 2024Using High-Level Patterns to Estimate How Humans Predict a Robot will Behavecited by 0
  27. 2025AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuitcited by 0
  28. 2025CooT: Learning to Coordinate In-Context with Coordination Transformerscited by 0
  29. 2025Remembering the Markov Property in Cooperative MARLcited by 0
  30. 2025Strategic Communication under Threat: Learning Information Trade-offs in Pursuit-Evasion Gamescited by 0
  31. 2025PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamworkcited by 0
  32. 2025PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamworkcited by 0
  33. 2025Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settingscited by 0
  34. 2026NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teamingcited by 0
  35. 2026Learning When to Cooperate Under Heterogeneous Goalscited by 0
  36. 2026SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Modelcited by 0
  37. 2026WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Viewscited by 0
  38. 2026Generalized Intention Modeling in Multi-Agent Reinforcement Learningcited by 0

50 most cited of 56 All 56 (JSON)