# Learning to Coordinate without Communication under Incomplete Information

arXiv: https://arxiv.org/abs/2409.12397 · HTML: https://mlsanity.com/paper/2409.12397/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings](https://mlsanity.com/paper/1704.07130/) (2017)
- [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://mlsanity.com/paper/2312.15224/) (2023)
- [No Press Diplomacy: Modeling Multi-Agent Gameplay](https://mlsanity.com/paper/1909.02128/) (2019)
- [Efficient Human-AI Coordination via Preparatory Language-based Convention](https://mlsanity.com/paper/2311.00416/) (2023)
- [Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication](https://mlsanity.com/paper/2405.14173/) (2024)
- [A New Model of Plan Recognition](https://mlsanity.com/paper/1301.6700/) (2013)

## Abstract (arXiv)

Achieving seamless coordination in cooperative games is a crucial challenge in artificial intelligence, particularly when players operate under incomplete information. While communication helps, it is not always feasible. In this paper, we explore how effective coordination can be achieved without verbal communication, relying solely on observing each other's actions. Our method enables an agent to develop a strategy by interpreting its partner's action sequences as intent signals, constructing a finite-state transducer built from deterministic finite automata, one for each possible action the agent can take. Experiments show that these strategies significantly outperform uncoordinated ones and closely match the performance of coordinating via direct communication.