.png){kind=icon}
返回
A sequential multi-agent reinforcement learning framework for different action spaces
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2024.125138.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In many real-world decision-making tasks, multi-agent need to learn collaboration in a high-dimensional complex action space, rather than just a single discrete action space. Recently, value decomposition learning methods such as QMIX have emerged as a promising approaches for collaborative multi-agent tasks. However, most of the value decomposition algorithms can only be used in discrete action space, which would limit their practicability. To address the limitation, we propose a novel algorithm called Multi-Agent Sequential Q-Networks (MASQN), which can be applied to the multi-agent domains with continuous, multidiscrete or hybrid action spaces. The proposed algorithm is based on the structure of centralized training with decentralized execution (CTDE). The decentralized actors ensure adaptability to different action spaces by utilizing action space discretization and sequential models, and the centralized critic utilizes the value decomposition architecture to guide effective updates of the policy parameters for each agent. We also give the convergence of joint policy from the perspective of policy iteration, by combining it with the CTDE structure and the constraint of the Individual Global Max (IGM) condition. Finally, we evaluate the MASQN algorithm on two benchmark environments: MAMuJoCo and Hybrid Predator-Prey. The empirical results show that MASQN out performs the state-of-the-art performance on three different action spaces.
Keyword:
Multi-agent reinforcement learning
Value decomposition learning
Different action space
Sequential model
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
Multi-agent reinforcement learning as a rehearsal for decentralized planning多智能体强化学习作为分散计划的演练.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Nash double Q-based multi-agent deep reinforcement learning for interactive in mixed traffic基于Nash双Q的混合流量交互多agent深度强化学习
PREAI
分享收藏Safe Reinforcement Learning With Stability Guarantee for Motion Planning of Autonomous Vehicles
PREAI
分享收藏分享收藏
查看更多内容