arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.05296cs.AI
收藏

基于价值分解网络的多Agent协作学习

Value-Decomposition Networks For Cooperative Multi-Agent Learning

DeepMind;University of Liverpool(利物浦大学)

Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z. Leibo, Karl Tuyls, Thore Graepel

摘要:

研究了具有单一联合奖励信号的协作多智能体强化学习问题。这类学习问题是困难的,因为通常很大的组合动作和观察空间。在完全集中和分散的方法中,我们发现了虚假奖励的问题和我们称之为“懒惰代理”问题的现象,这是由于部分可观测性而产生的。我们解决这些问题,通过训练个人代理与一种新的价值分解网络架构,学会分解成代理明智的价值函数的团队价值函数。我们在一系列部分可观察的多智能体领域进行了实验评估,并表明学习这种值分解会带来更好的结果,特别是当与权重共享,角色信息和信息渠道相结合时。

英文摘要:

We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully centralized and decentralized approaches, we find the problem of spurious rewards and a phenomenon we call the "lazy agent" problem, which arises due to partial observability. We address these problems by training individual agents with a novel value decomposition network architecture, which learns to decompose the team value function into agent-wise value functions. We perform an experimental evaluation across a range of partially-observable multi-agent domains and show that learning such value-decompositions leads to superior results, in particular when combined with weight sharing, role information and information channels.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑