Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication
This addresses the challenge of human-agent cooperation in strategic games with information asymmetry, though it is incremental as it builds on existing methods like Monte Carlo tree search.
The paper tackles the problem of enabling autonomous agents to cooperate with humans in games with incomplete information by developing a communication-based approach that uses natural language to bridge information gaps. Results from human experiments show that this approach reduces the number of turns needed for cooperation, improving efficiency.
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.