L2E: Learning to Exploit Your Opponent

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.

References in corpus (11)

• Trust Region Policy Optimization
• On First-Order Meta-Learning Algorithms
• Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems
• Robust Adversarial Reinforcement Learning
• Learning to reinforcement learn
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• Unsupervised Meta-Learning for Reinforcement Learning
• Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning
• Wasserstein Robust Reinforcement Learning
• Single Deep Counterfactual Regret Minimization