Dual Self-awareness Value Decomposition Framework Without Individual Global Max For Cooperative Multi-agent Reinforcement Learning
2023 · Zhiwei Xu, Bin Zhang, Dapeng Li, et al.
Abstract
Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise. Each agent consists of an ego policy for action selection and an alter ego value function to solve the credit assignment problem. The value function factorization can ignore the IGM assumption by utilizing an explicit search procedure. On the basis of the above, we also suggest a novel anti-ego exploration mechanism to avoid the algorithm becoming stuck in a local optimum. As the first fully IGM-free value decomposition method, our proposed framework achieves desirable performance in various cooperative tasks.
Authors
(none)
Tags
Stats
Related papers
- Understanding Value Decomposition Algorithms In Deep Cooperative Multi-agent Reinforcement Learning (2022)0.00
- Adaptive Value Decomposition With Greedy Marginal Contribution Computation For Cooperative Multi-agent Reinforcement Learning (2023)3.58
- Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)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
- VDFD: Multi-agent Value Decomposition Framework With Disentangled World Model (2023)0.00
- Rethinking Individual Global Max In Cooperative Multi-agent Reinforcement Learning (2022)0.00
- SVDE: Scalable Value-decomposition Exploration For Cooperative Multi-agent Reinforcement Learning (2023)0.00