Automatic Bridge Bidding Using Deep Reinforcement Learning

TL;DR

This paper introduces a novel deep reinforcement learning system for bridge bidding that learns directly from raw card data without relying on human-designed bidding conventions, outperforming existing computer programs.

Contribution

It presents the first AI bridge bidding system that learns autonomously from raw data using deep reinforcement learning, surpassing traditional rule-based systems.

Findings

Outperforms champion-winning computer bridge programs

Learns effective bidding strategies without human domain knowledge

Balances exploration and exploitation successfully

Abstract

Bridge is among the zero-sum games for which artificial intelligence has not yet outperformed expert human players. The main difficulty lies in the bidding phase of bridge, which requires cooperative decision making under partial information. Existing artificial intelligence systems for bridge bidding rely on and are thus restricted by human-designed bidding systems or features. In this work, we propose a pioneering bridge bidding system without the aid of human domain knowledge. The system is based on a novel deep reinforcement learning model, which extracts sophisticated features and learns to bid automatically based on raw card data. The model includes an upper-confidence-bound algorithm and additional techniques to achieve a balance between exploration and exploitation. Our experiments validate the promising performance of our proposed model. In particular, the model advances from having no knowledge about bidding to achieving superior performance when compared with a champion-winning computer bridge program that implements a human-designed bidding system.