Enhancement of Cooperation Using Latent Strategies in Multi-Agent Deep Reinforcement Learning

Bachelor Thesis

January 2024 - July 2024

Advised by Gentoku Nakasone, supervised by Toshiharu Sugawara

Will be published in an IEICE journal

In this project, we propose a distributed reinforcement learning method in a multi-agent environment that reflects policies based on the latent representations of other agents through actions. Many real-world multi-agent systems include various agents with pre-learned behaviors or agents with strategies that are pre-encoded and do not change during interactions, requiring coordination with each of them individually. Our proposed method uses neural network-based encoders and decoders to identify the latent policies of other agents from high-dimensional observations in the early stages of coexisting interactions, and then determines the agent's own actions based on this information. This allows for rational decision-making that adapts to the behavior patterns of other agents.