Model-Based Opponent Modeling
arXiv:2108.01843
Abstract
When one agent interacts with a multi-agent environment, it is challenging to deal with various opponents unseen before. Modeling the behaviors, goals, or beliefs of opponents could help the agent adjust its policy to adapt to different opponents. In addition, it is also important to consider opponents who are learning simultaneously or capable of reasoning. However, existing work usually tackles only one of the aforementioned types of opponents. In this paper, we propose model-based opponent modeling (MBOM), which employs the environment model to adapt to all kinds of opponents. MBOM simulates the recursive reasoning process in the environment model and imagines a set of improving opponent policies. To effectively and accurately represent the opponent policy, MBOM further mixes the imagined opponent policies according to the similarity with the real behaviors of opponents. Empirically, we show that MBOM achieves more effective adaptation than existing methods in a variety of tasks, respectively with different types of opponents, i.e., fixed policy, naïve learner, and reasoning learner.
21 pages, 10 figures
References in corpus (7)
- Distilling the Knowledge in a Neural Network
- Reinforcement Learning with Unsupervised Auxiliary Tasks
- On-line Policy Improvement using Monte-Carlo Search
- Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning
- Emergence of Pragmatics from Referential Game between Theory of Mind Agents
- A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
- Variational Autoencoders for Opponent Modeling in Multi-Agent Systems