Back to Search
Start Over
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- Source :
- Journal of Machine Learning Research 21(178):1-51, 2020
- Publication Year :
- 2020
-
Abstract
- 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.<br />Comment: Extended version of the ICML 2018 conference paper (arXiv:1803.11485)
Details
- Database :
- arXiv
- Journal :
- Journal of Machine Learning Research 21(178):1-51, 2020
- Publication Type :
- Report
- Accession number :
- edsarx.2003.08839
- Document Type :
- Working Paper