Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
SMAC SMAC 27m_vs_30m QMIX Median Win Rate 49 # 7
SMAC SMAC 3s5z_vs_3s6z QMIX Median Win Rate 2 # 10
SMAC SMAC 6h_vs_8z QMIX Median Win Rate 3 # 6
SMAC SMAC corridor QMIX Median Win Rate 1 # 10
SMAC SMAC MMM2 QMIX Median Win Rate 69 # 9

Methods


No methods listed for this paper. Add relevant methods here