paper-with-me

홈 › Papers

AgentMixer: Multi-Agent Correlated Policy Factorization

2024-01-16 · Zhiyuan Li, Wenshuai Zhao, Lijun Wu, Joni Pajarinen

In multi-agent reinforcement learning, centralized training with decentralized execution (CTDE) methods typically assume that agents make decisions based on their local observations independently, which may not lead to a correlated joint policy with coordination. Coordination can be explicitly encouraged during training and individual policies can be trained to imitate the correlated joint policy. However, this may lead to an \textit{asymmetric learning failure} due to the observation mismatch between the joint and individual policies. Inspired by the concept of correlated equilibrium, we introduce a \textit{strategy modification} called AgentMixer that allows agents to correlate their policies. AgentMixer combines individual partially observable policies into a joint fully observable policy non-linearly. To enable decentralized execution, we introduce \textit{Individual-Global-Consistency} to guarantee mode consistency during joint training of the centralized and decentralized policies and prove that AgentMixer converges to an $\epsilon$-approximate Correlated Equilibrium. In the Multi-Agent MuJoCo, SMAC-v2, Matrix Game, and Predator-Prey benchmarks, AgentMixer outperforms or matches state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2401.08728

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningMuJoCoMulti-agent Reinforcement LearningSMACSMAC+

Similar Papers 제목 키워드 기반

More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization

2022-09-26 · Jiangxing Wang, Deheng Ye, Zongqing Lu

In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Giv…

Multi-agent Reinforcement Learning

Multi-Agent MDP Homomorphic Networks

2021-10-09 · ICLR 2022 4 · Elise van der Pol, Herke van Hoof, Frans A. Oliehoek, Max Welling

This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience between global symmetries in the joint state…

B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning

2025-01-30 · Woojun Kim, Katia Sycara

Overestimation arising from selecting unseen actions during policy evaluation is a major challenge in offline reinforcement learning (RL). A minimalist approach in the single-agent setting -- adding behavior cloning (BC)…

Multi-agent Reinforcement LearningReinforcement Learning (RL)

The Performance Impact of Combining Agent Factorization with Different Learning Algorithms for Multiagent Coordination

2022-09-09 · SETN 2022 9 · Andreas Kallinteris, Stavros Orfanoudakis, Georgios Chalkiadakis

Factorizing a multiagent system refers to partitioning the state- action space to individual agents and defining the interactions be- tween those agents. This so-called agent factorization is of much im- portance in r…

ManagementPolicy Gradient Methods

QFree: A Universal Value Function Factorization for Multi-Agent Reinforcement Learning

2023-11-01 · Rizhong Wang, Huiping Li, Di Cui, Demin Xu

Centralized training is widely utilized in the field of multi-agent reinforcement learning (MARL) to assure the stability of training process. Once a joint policy is obtained, it is critical to design a value function fa…

Multi-agent Reinforcement Learningreinforcement-learningSMACSMAC++1