mlsanityData to 14 Oct 2026

Learning Latent Representations to Influence Multi-Agent Interaction

arXiv 2011.06619 ↗First posted 12 Nov 2020cs.RO cs.AI cs.LGcited by 93

Not on the map. Why?

Abstract (arXiv)

Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans, we recognize that robots do not need to explicitly model every low-level action another agent will make; instead, we can capture the latent strategy of other agents through high-level representations. We propose a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy. The ego agent then leverages these latent dynamics to influence the other agent, purposely guiding them towards policies suitable for co-adaptation. Across several simulated domains and a real-world air hockey game, our approach outperforms the alternatives and learns to influence the other agent.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 24; 2023: 17; 2024: 14; 2025: 15; 2026: 9.

93 papers.

Sort:

By area:

  1. 2022Evaluating Human-Language Model Interactioncited by 92
  2. 2022Efficient Video Prediction via Sparsely Conditioned Flow Matchingcited by 55
  3. 2024Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Samplingcited by 52
  4. 2022Model-Free Opponent Shapingcited by 44
  5. 2022A Survey of Ad Hoc Teamwork Researchcited by 43
  6. 2021AGENT: A Benchmark for Core Psychological Reasoningcited by 42
  7. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  8. 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biasedcited by 37
  9. 2021Social Coordination and Altruism in Autonomous Drivingcited by 28
  10. 2021Influencing Towards Stable Multi-Agent Interactionscited by 24
  11. 2022PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaborationcited by 23
  12. 2022Influencing Long-Term Behavior in Multiagent Reinforcement Learningcited by 18
38 more
  1. 2025Curating Demonstrations using Online Experiencecited by 18
  2. 2021Co-GAIL: Learning Diverse Strategies for Human-Robot Collaborationcited by 17
  3. 2022Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Trafficcited by 15
  4. 2023Online Learning in Stackelberg Games with an Omniscient Followercited by 15
  5. 2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
  6. 2021Playful Interactions for Representation Learningcited by 13
  7. 2022Conditional Imitation Learning for Multi-Agent Gamescited by 13
  8. 2022Learning Representations that Enable Generalization in Assistive Taskscited by 13
  9. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 13
  10. 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperationcited by 13
  11. 2021Emergent Prosociality in Multi-Agent Games Through Giftingcited by 12
  12. 2021Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Criticcited by 11
  13. 2023Towards Modeling and Influencing the Dynamics of Human Learningcited by 11
  14. 2023Learning Vision-based Pursuit-Evasion Robot Policiescited by 11
  15. 2024Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedbackcited by 11
  16. 2023Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimationcited by 10
  17. 2021LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammatescited by 9
  18. 2022Leveraging Smooth Attention Prior for Multi-Agent Trajectory Predictioncited by 9
  19. 2022RILI: Robustly Influencing Latent Intentcited by 8
  20. 2023Cooperative AI via Decentralized Commitment Devicescited by 7
  21. 2024Fast Peer Adaptation with Context-aware Explorationcited by 7
  22. 2024Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racingcited by 7
  23. 2024Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inferencecited by 7
  24. 2022Prediction-aware and Reinforcement Learning based Altruistic Cooperative Drivingcited by 6
  25. 2022CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spacescited by 6
  26. 2024Open Ad Hoc Teamwork with Cooperative Game Theorycited by 6
  27. 2024Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowdscited by 6
  28. 2021Dealing with Non-Stationarity in MARL via Trust-Region Decompositioncited by 5
  29. 2022Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibriacited by 5
  30. 2022Learning Latent Representations to Co-Adapt to Humanscited by 5
  31. 2023iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learningcited by 5
  32. 2024IDIL: Imitation Learning of Intent-Driven Expert Behaviorcited by 5
  33. 2021Towards Learning Generalizable Driving Policies from Restricted Latent Representationscited by 4
  34. 2022LOPR: Latent Occupancy PRediction using Generative Modelscited by 4
  35. 2023MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learningcited by 4
  36. 2023PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systemscited by 4
  37. 2024Multi-agent cooperation through learning-aware policy gradientscited by 4
  38. 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)cited by 4

50 most cited of 93 All 93 (JSON)