QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, 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 network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations. We structurally enforce that the joint-action value is monotonic in the per-agent values, which allows tractable maximisation of the joint action-value in off-policy learning, and guarantees consistency between the centralised and decentralised policies. We evaluate QMIX on a challenging set of StarCraft II micromanagement tasks, and show that QMIX significantly outperforms existing value-based multi-agent reinforcement learning methods.
PDF Abstract ICML 2018 PDF ICML 2018 AbstractCode
Colab
Datasets
StarCraft II Learning Environment
SMAC-Exp
Def_Infantry_parallel
Def_Infantry_sequential
Def_Outnumbered_sequential
Def_Armored_sequential
Off_Superhard_parallel
Def_Outnumbered_parallel
Off_Hard_parallel
Def_Armored_parallel
Off_Complicated_parallel
Off_Distant_parallel
Off_Near_parallel
Off_Superhard_sequential
Off_Near_sequential
Off_Distant_sequential
Off_Hard_sequential
Off_Complicated_sequential
