DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
This work addresses stochastic environments in multi-agent systems, offering a novel approach for researchers in MARL, though it appears incremental as it builds on existing factorization methods.
The paper tackles the challenge of high stochasticity in cooperative multi-agent reinforcement learning by proposing the DFAC framework, which integrates distributional RL with value function factorization to model returns as random variables, and it outperforms baselines on StarCraft Multi-Agent Challenge tasks.
In fully cooperative multi-agent reinforcement learning (MARL) settings, the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents. To address the above issues, we integrate distributional RL and value function factorization methods by proposing a Distributional Value Function Factorization (DFAC) framework to generalize expected value function factorization methods to their DFAC variants. DFAC extends the individual utility functions from deterministic variables to random variables, and models the quantile function of the total return as a quantile mixture. To validate DFAC, we demonstrate DFAC's ability to factorize a simple two-step matrix game with stochastic rewards and perform experiments on all Super Hard tasks of StarCraft Multi-Agent Challenge, showing that DFAC is able to outperform expected value function factorization baselines.