Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning
This work addresses sample efficiency issues in multi-agent reinforcement learning, which is incremental as it builds on existing value decomposition methods.
The paper tackles the challenge of applying model-based reinforcement learning to multi-agent systems, where environmental complexity and compounding errors hinder learning, by proposing an implicit model-based method that improves sample efficiency across various partially observable Markov decision process domains.
Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding error may hinder the learning process when model-based methods are applied to multi-agent tasks. This paper proposes an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states in the latent space, making agents have the foresight. Our approach can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in different partially observable Markov decision process domains.