arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.08839cs.LGcs.MAstat.ML
收藏

深度多智能体强化学习的单调价值函数分解

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

University of Oxford(牛津大学);Russian-Armenian University(俄罗斯-亚美尼亚大学);Facebook AI Research(脸书人工智能研究院)

Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Shimon Whiteson

摘要:

在许多现实世界中,一个代理团队必须协调其行为,同时以分散的方式行事。同时,通常可以以集中的方式训练代理,其中全局状态信息可用并且通信约束被解除。学习以额外状态信息为条件的联合动作值是利用集中式学习的一种有吸引力的方法,但提取分散式策略的最佳策略尚不清楚。我们的解决方案是QMIX,这是一种新颖的基于价值的方法,可以以集中的端到端方式训练分散的策略。QMIX采用混合网络,将联合动作值估计为每个代理值的单调组合。通过在混合网络中使用非负权重,我们在结构上强制联合行动值在每个代理值中是单调的,这保证了集中式和分散式政策之间的一致性。为了评估QMIX的性能,我们提出了星际争霸多智能体挑战赛(SMAC)作为深度多智能体强化学习的新基准。我们评估QMIX的一组具有挑战性的SMAC场景,并表明它显着优于现有的多智能体强化学习方法。

英文摘要:

In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a mixing network that estimates joint action-values as a monotonic combination of per-agent values. We structurally enforce that the joint-action value is monotonic in the per-agent values, through the use of non-negative weights in the mixing network, which guarantees consistency between the centralised and decentralised policies. To evaluate the performance of QMIX, we propose the StarCraft Multi-Agent Challenge (SMAC) as a new benchmark for deep multi-agent reinforcement learning. We evaluate QMIX on a challenging set of SMAC scenarios and show that it significantly outperforms existing multi-agent reinforcement learning methods.

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。

↑