Human-Agent Cooperation in Bridge Bidding
This work addresses the challenge of creating AI agents that can effectively cooperate with human players in complex cooperative games, which is a significant problem for AI research in human-computer interaction.
This paper tackles the problem of human-agent cooperation in bridge bidding. The authors developed a reinforcement learning agent that achieves state-of-the-art performance in three settings: agent-agent, agent-bot, and agent-human partnerships.
We introduce a human-compatible reinforcement-learning approach to a cooperative game, making use of a third-party hand-coded human-compatible bot to generate initial training data and to perform initial evaluation. Our learning approach consists of imitation learning, search, and policy iteration. Our trained agents achieve a new state-of-the-art for bridge bidding in three settings: an agent playing in partnership with a copy of itself; an agent partnering a pre-existing bot; and an agent partnering a human player.