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.
@article{arxiv.2011.14124,
title = {Human-Agent Cooperation in Bridge Bidding},
author = {Edward Lockhart and Neil Burch and Nolan Bard and Sebastian Borgeaud and Tom Eccles and Lucas Smaira and Ray Smith},
journal= {arXiv preprint arXiv:2011.14124},
year = {2020}
}