MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning

Understand

In the real world, many tasks require multiple agents to cooperate with each other under the condition of local observations.

• To solve such problems, many multi-agent reinforcement learning methods based on Centralized Training with Decentralized Execution have been proposed.
• One representative class of work is value decomposition, which decomposes the global joint Q-value $Q_\text{jt}$ into individual Q-values $Q_a$ to guide individuals' behaviors, e.g.
• VDN (Value-Decomposition Networks) and QMIX.