L2E: Learning to Exploit Your Opponent

TL;DR

This paper introduces L2E, a novel framework for implicit opponent modeling that enables quick adaptation to unknown opponents in strategic games through limited interactions during training.

Contribution

L2E is the first framework to enable rapid adaptation to unknown opponents by learning from few interactions, using an automatic opponent strategy generation algorithm.

Findings

L2E quickly adapts to diverse opponent styles.

L2E outperforms existing methods in benchmark games.

The automatic opponent generation improves training effectiveness.

Abstract

Opponent modeling is essential to exploit sub-optimal opponents in strategic interactions. Most previous works focus on building explicit models to directly predict the opponents' styles or strategies, which require a large amount of data to train the model and lack adaptability to unknown opponents. In this work, we propose a novel Learning to Exploit (L2E) framework for implicit opponent modeling. L2E acquires the ability to exploit opponents by a few interactions with different opponents during training, thus can adapt to new opponents with unknown styles during testing quickly. We propose a novel opponent strategy generation algorithm that produces effective opponents for training automatically. We evaluate L2E on two poker games and one grid soccer game, which are the commonly used benchmarks for opponent modeling. Comprehensive experimental results indicate that L2E quickly adapts to diverse styles of unknown opponents.