# Learning Latent Representations to Influence Multi-Agent Interaction

arXiv: https://arxiv.org/abs/2011.06619 · HTML: https://mlsanity.com/paper/2011.06619/

## Key facts

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

## Built on by (most cited first, 30 of 93)

- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [Efficient Video Prediction via Sparsely Conditioned Flow Matching](https://mlsanity.com/paper/2211.14575/) (2022)
- [Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling](https://mlsanity.com/paper/2408.17355/) (2024)
- [Model-Free Opponent Shaping](https://mlsanity.com/paper/2205.01447/) (2022)
- [A Survey of Ad Hoc Teamwork Research](https://mlsanity.com/paper/2202.10450/) (2022)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Learning to Ground Multi-Agent Communication with Autoencoders](https://mlsanity.com/paper/2110.15349/) (2021)
- [Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased](https://mlsanity.com/paper/2302.01605/) (2023)
- [Social Coordination and Altruism in Autonomous Driving](https://mlsanity.com/paper/2107.00200/) (2021)
- [Influencing Towards Stable Multi-Agent Interactions](https://mlsanity.com/paper/2110.08229/) (2021)
- [PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration](https://mlsanity.com/paper/2203.08553/) (2022)
- [Influencing Long-Term Behavior in Multiagent Reinforcement Learning](https://mlsanity.com/paper/2203.03535/) (2022)
- [Curating Demonstrations using Online Experience](https://mlsanity.com/paper/2503.03707/) (2025)
- [Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration](https://mlsanity.com/paper/2108.06038/) (2021)
- [Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic](https://mlsanity.com/paper/2202.00881/) (2022)
- [Online Learning in Stackelberg Games with an Omniscient Follower](https://mlsanity.com/paper/2301.11518/) (2023)
- [Multi-Agent Policy Transfer via Task Relationship Modeling](https://mlsanity.com/paper/2203.04482/) (2022)
- [Playful Interactions for Representation Learning](https://mlsanity.com/paper/2107.09046/) (2021)
- [Conditional Imitation Learning for Multi-Agent Games](https://mlsanity.com/paper/2201.01448/) (2022)
- [Learning Representations that Enable Generalization in Assistive Tasks](https://mlsanity.com/paper/2212.03175/) (2022)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025)
- [Emergent Prosociality in Multi-Agent Games Through Gifting](https://mlsanity.com/paper/2105.06593/) (2021)
- [Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic](https://mlsanity.com/paper/2107.05664/) (2021)
- [Towards Modeling and Influencing the Dynamics of Human Learning](https://mlsanity.com/paper/2301.00901/) (2023)
- [Learning Vision-based Pursuit-Evasion Robot Policies](https://mlsanity.com/paper/2308.16185/) (2023)
- [Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback](https://mlsanity.com/paper/2410.08852/) (2024)
- [Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation](https://mlsanity.com/paper/2311.16091/) (2023)
- [LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates](https://mlsanity.com/paper/2109.12508/) (2021)
- [Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction](https://mlsanity.com/paper/2203.04421/) (2022)

## 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.