ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games
This work addresses offline learning efficiency for zero-sum games, where opponent strategies critically affect outcomes, representing a domain-specific incremental improvement.
The paper tackles the problem of offline learning in zero-sum games by estimating the exploited level of trajectories from diverse demonstrators to identify dominant strategies, resulting in significant enhancements to imitation learning and offline reinforcement learning algorithms.
Offline learning has become widely used due to its ability to derive effective policies from offline datasets gathered by expert demonstrators without interacting with the environment directly. Recent research has explored various ways to enhance offline learning efficiency by considering the characteristics (e.g., expertise level or multiple demonstrators) of the dataset. However, a different approach is necessary in the context of zero-sum games, where outcomes vary significantly based on the strategy of the opponent. In this study, we introduce a novel approach that uses unsupervised learning techniques to estimate the exploited level of each trajectory from the offline dataset of zero-sum games made by diverse demonstrators. Subsequently, we incorporate the estimated exploited level into the offline learning to maximize the influence of the dominant strategy. Our method enables interpretable exploited level estimation in multiple zero-sum games and effectively identifies dominant strategy data. Also, our exploited level augmented offline learning significantly enhances the original offline learning algorithms including imitation learning and offline reinforcement learning for zero-sum games.