VDFD: Multi-agent Value Decomposition Framework With Disentangled World Model
2023 · Zhizun Wang, David Meger
Abstract
In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge of achieving a common goal of multiple agents interacting in the same environment with reduced sample complexity. Due to scalability and non-stationarity problems posed by multi-agent systems, model-free methods rely on a considerable number of samples for training. In contrast, we use a modularized world model, composed of action-conditioned, action-free, and static branches, to unravel the complicated environment dynamics. Our model produces imagined outcomes based on past experience, without sampling directly from the real environment. We employ variational auto-encoders and variational graph auto-encoders to learn the latent representations for the world model, which is merged with a value-based framework to predict the joint action-value function and optimize the overall training objective. Experimental
Authors
(none)
Tags
Stats
Related papers
- SVDE: Scalable Value-decomposition Exploration For Cooperative Multi-agent Reinforcement Learning (2023)0.00
- Mingling Foresight With Imagination: Model-based Cooperative Multi-agent Reinforcement Learning (2022)0.00
- Dual Self-awareness Value Decomposition Framework Without Individual Global Max For Cooperative Multi-agent Reinforcement Learning (2023)0.00
- Heterogeneous Value Decomposition Policy Fusion For Multi-agent Cooperation (2025)0.00
- Contrastive Identity-aware Learning For Multi-agent Value Decomposition (2022)9.41
- A Unified Framework For Factorizing Distributional Value Functions For Multi-agent Reinforcement Learning (2023)0.00
- Boosting Value Decomposition Via Unit-wise Attentive State Representation For Cooperative Multi-agent Reinforcement Learning (2023)0.00
- Dynamic Value Estimation For Single-task Multi-scene Reinforcement Learning (2020)0.00