Variational Autoencoders For Opponent Modeling In Multi-agent Systems

Abstract

Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact with the other agents that have fixed policies. Modeling the behavior of other agents (opponents) is essential in understanding the interactions of the agents in the system. By taking advantage of recent advances in unsupervised learning, we propose modeling opponents using variational autoencoders. Additionally, many existing methods in the literature assume that the opponent models have access to opponent's observations and actions during both training and execution. To eliminate this assumption, we propose a modification that attempts to identify the underlying opponent model using only local information of our agent, such as its observations, actions, and rewards. The experiments indicate that our opponent modeling methods achieve equal or great

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypapoudakis2020variational

Related papers

• Model-based Opponent Modeling (2021)0.00
• Learning To Model Opponent Learning (2020)0.00
• Metric Policy Representations For Opponent Modeling (2021)0.00
• Consistent Opponent Modeling In Imperfect-information Games (2025)0.00
• Double Deep Q-learning In Opponent Modeling (2022)0.00
• Opponent Learning Awareness And Modelling In Multi-objective Normal Form Games (2020)7.16
• Robust Opponent Modeling Via Adversarial Ensemble Reinforcement Learning In Asymmetric Imperfect-information Games (2019)0.00
• Preference-based Opponent Shaping In Differentiable Games (2024)2.26