Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

TL;DR

This paper introduces QMIX, a novel value-based method for deep multi-agent reinforcement learning that enables decentralised policies trained centrally, using a monotonic value function factorisation to ensure consistency and improve performance.

Contribution

QMIX presents a new value function factorisation approach with a monotonicity constraint, enabling effective decentralised policy learning from centralised training in multi-agent settings.

Findings

QMIX outperforms existing methods on the SMAC benchmark.

The monotonic mixing network guarantees consistency between centralised and decentralised policies.

QMIX achieves significant performance improvements in complex multi-agent scenarios.

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.