# Relational Forward Models for Multi-Agent Learning

arXiv: https://arxiv.org/abs/1809.11044 · HTML: https://mlsanity.com/paper/1809.11044/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2018.

## Built on by (most cited first, 21 of 21)

- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [Neural Production Systems: Learning Rule-Governed Visual Dynamics](https://mlsanity.com/paper/2103.01937/) (2021)
- [Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning](https://mlsanity.com/paper/2107.00848/) (2021)
- [Discrete-Valued Neural Communication](https://mlsanity.com/paper/2107.02367/) (2021)
- [Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2404.10976/) (2024)
- [Interaction Modeling with Multiplex Attention](https://mlsanity.com/paper/2208.10660/) (2022)
- [A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning](https://mlsanity.com/paper/2210.05448/) (2022)
- [3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes](https://mlsanity.com/paper/2304.11470/) (2023)
- [Understanding Physical Dynamics with Counterfactual World Modeling](https://mlsanity.com/paper/2312.06721/) (2023)
- [SPARTAN: A Sparse Transformer World Model Attending to What Matters](https://mlsanity.com/paper/2411.06890/) (2024)
- [Joint Attention for Multi-Agent Coordination and Social Learning](https://mlsanity.com/paper/2104.07750/) (2021)
- [Detecting and Adapting to Novelty in Games](https://mlsanity.com/paper/2106.02204/) (2021)
- [Open Ad Hoc Teamwork with Cooperative Game Theory](https://mlsanity.com/paper/2402.15259/) (2024)
- [Compete and Compose: Learning Independent Mechanisms for Modular World Models](https://mlsanity.com/paper/2404.15109/) (2024)
- [CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning](https://mlsanity.com/paper/2306.11128/) (2023)
- [Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis](https://mlsanity.com/paper/2504.12777/) (2025)
- [Neural Interaction Energy for Multi-Agent Trajectory Prediction](https://mlsanity.com/paper/2404.16579/) (2024)
- [Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations](https://mlsanity.com/paper/2510.13982/) (2025)
- [Policy Dispersion in Non-Markovian Environment](https://mlsanity.com/paper/2302.14509/) (2023)
- [Communication Learning in Multi-Agent Systems from Graph Modeling Perspective](https://mlsanity.com/paper/2411.00382/) (2024)
- [Generalized Intention Modeling in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.31318/) (2026)

## Abstract (arXiv)

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predictions of agents' future behavior in multi-agent environments. Because these models operate on the discrete entities and relations present in the environment, they produce interpretable intermediate representations which offer insights into what drives agents' behavior, and what events mediate the intensity and valence of social interactions. Furthermore, we show that embedding RFM modules inside agents results in faster learning systems compared to non-augmented baselines. As more and more of the autonomous systems we develop and interact with become multi-agent in nature, developing richer analysis tools for characterizing how and why agents make decisions is increasingly necessary. Moreover, developing artificial agents that quickly and safely learn to coordinate with one another, and with humans in shared environments, is crucial.