Robust Opponent Modeling Via Adversarial Ensemble Reinforcement Learning In Asymmetric Imperfect-information Games

Abstract

This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself and its ally). In order to maximize the reward, the protagonist agent has to infer the opponent type through agent modeling. We use multiagent reinforcement learning (MARL) to learn opponent models through self-play, which captures the full strategy interaction and reasoning between agents. However, agent policies learned from self-play can suffer from mutual overfitting. Ensemble training methods can be used to improve the robustness of agent policy against different opponents, but it also significantly increases the computational overhead. In order to achieve a good trade-off between the robustness of the learned policy and the computation complexity, we propose to train a separate opponent policy against the protagonist agent for evaluation purpo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshen2019robust

Related papers

• Consistent Opponent Modeling In Imperfect-information Games (2025)0.00
• Robust Model-based Reinforcement Learning With An Adversarial Auxiliary Model (2024)0.00
• Byzantine Robust Cooperative Multi-agent Reinforcement Learning As A Bayesian Game (2023)0.00
• Toward Evaluating Robustness Of Reinforcement Learning With Adversarial Policy (2023)4.52
• Robust Multi-agent Reinforcement Learning Via Adversarial Regularization: Theoretical Foundation And Stable Algorithms (2023)2.98
• Online Robust Policy Learning In The Presence Of Unknown Adversaries (2018)0.00
• Learning To Model Opponent Learning (2020)0.00
• Preventing Imitation Learning With Adversarial Policy Ensembles (2020)0.00