# Who Needs to Know? Minimal Knowledge for Optimal Coordination

arXiv: https://arxiv.org/abs/2306.09309 · HTML: https://mlsanity.com/paper/2306.09309/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (2020)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL](https://mlsanity.com/paper/2110.14555/) (2021)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Learning Efficient Multi-agent Communication: An Information Bottleneck Approach](https://mlsanity.com/paper/1911.06992/) (2019)
- [On the Importance of Environments in Human-Robot Coordination](https://mlsanity.com/paper/2106.10853/) (2021)
- [A New Formalism, Method and Open Issues for Zero-Shot Coordination](https://mlsanity.com/paper/2106.06613/) (2021)
- [Learning Agent Communication under Limited Bandwidth by Message Pruning](https://mlsanity.com/paper/1912.05304/) (2019)
- [Reasoning about Hypothetical Agent Behaviours and their Parameters](https://mlsanity.com/paper/1906.11064/) (2019)
- [Graphical Models for Game Theory](https://mlsanity.com/paper/1301.2281/) (2013)
- [Equivariant Networks for Zero-Shot Coordination](https://mlsanity.com/paper/2210.12124/) (2022)
- [Legible Normativity for AI Alignment: The Value of Silly Rules](https://mlsanity.com/paper/1811.01267/) (2018)
- [Multi-Agent Fully Decentralized Value Function Learning with Linear Convergence Rates](https://mlsanity.com/paper/1810.07792/) (2018)
- [On-the-fly Strategy Adaptation for ad-hoc Agent Coordination](https://mlsanity.com/paper/2203.08015/) (2022)

## Built on by (most cited first, 5 of 5)

- [JaxMARL: Multi-Agent RL Environments and Algorithms in JAX](https://mlsanity.com/paper/2311.10090/) (2023)
- [ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination](https://mlsanity.com/paper/2310.05208/) (2023)
- [Symmetry-Breaking Augmentations for Ad Hoc Teamwork](https://mlsanity.com/paper/2402.09984/) (2024)
- [Robust and Diverse Multi-Agent Learning via Rational Policy Gradient](https://mlsanity.com/paper/2511.09535/) (2025)
- [CooT: Learning to Coordinate In-Context with Coordination Transformers](https://mlsanity.com/paper/2506.23549/) (2025)

## Abstract (arXiv)

To optimally coordinate with others in cooperative games, it is often crucial to have information about one's collaborators: successful driving requires understanding which side of the road to drive on. However, not every feature of collaborators is strategically relevant: the fine-grained acceleration of drivers may be ignored while maintaining optimal coordination. We show that there is a well-defined dichotomy between strategically relevant and irrelevant information. Moreover, we show that, in dynamic games, this dichotomy has a compact representation that can be efficiently computed via a Bellman backup operator. We apply this algorithm to analyze the strategically relevant information for tasks in both a standard and a partially observable version of the Overcooked environment. Theoretical and empirical results show that our algorithms are significantly more efficient than baselines. Videos are available at https://minknowledge.github.io.