Mingling Foresight With Imagination: Model-based Cooperative Multi-agent Reinforcement Learning
2022 · Zhiwei Xu, Dapeng Li, Bin Zhang, et al.
Abstract
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.
Authors
(none)
Tags
Stats
Related papers
- VDFD: Multi-agent Value Decomposition Framework With Disentangled World Model (2023)0.00
- Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00
- Innate-values-driven Reinforcement Learning Based Cooperative Multi-agent Cognitive Modeling (2024)0.00
- Adaptive Value Decomposition With Greedy Marginal Contribution Computation For Cooperative Multi-agent Reinforcement Learning (2023)3.58
- Efficient Model-based Multi-agent Reinforcement Learning Via Optimistic Equilibrium Computation (2022)0.00
- Reaching Consensus In Cooperative Multi-agent Reinforcement Learning With Goal Imagination (2024)0.00
- MMD-MIX: Value Function Factorisation With Maximum Mean Discrepancy For Cooperative Multi-agent Reinforcement Learning (2021)0.00
- Modeling Sensorimotor Coordination As Multi-agent Reinforcement Learning With Differentiable Communication (2019)0.00