Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication

TL;DR

This paper presents a natural language communication framework enabling autonomous agents to cooperate with humans in incomplete information games, improving collaboration efficiency through a language and planning module.

Contribution

It introduces a novel communication-based approach with a language module and a planning algorithm for human-agent cooperation under incomplete information.

Findings

Communication narrows the information gap between players.

Enhanced cooperation efficiency with fewer turns.

Effective natural language-based policy synthesis.

Abstract

Developing autonomous agents that can strategize and cooperate with humans under information asymmetry is challenging without effective communication in natural language. We introduce a shared-control game, where two players collectively control a token in alternating turns to achieve a common objective under incomplete information. We formulate a policy synthesis problem for an autonomous agent in this game with a human as the other player. To solve this problem, we propose a communication-based approach comprising a language module and a planning module. The language module translates natural language messages into and from a finite set of flags, a compact representation defined to capture player intents. The planning module leverages these flags to compute a policy using an asymmetric information-set Monte Carlo tree search with flag exchange algorithm we present. We evaluate the effectiveness of this approach in a testbed based on Gnomes at Night, a search-and-find maze board game. Results of human subject experiments show that communication narrows the information gap between players and enhances human-agent cooperation efficiency with fewer turns.