POWQMIX: Weighted Value Factorization with Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
This work addresses a key bottleneck in cooperative multi-agent reinforcement learning for domains like gaming and robotics, offering a theoretically guaranteed method to improve policy learning, though it is incremental as it builds on existing QMIX frameworks.
The paper tackles the limitation of monotonicity constraints in QMIX-based multi-agent reinforcement learning, which restrict value representation and optimal policy learning, by proposing POWQMIX, a weighted value factorization algorithm that recognizes potentially optimal joint actions and assigns higher training weights to them, achieving state-of-the-art performance in experiments on matrix games, predator-prey, and StarCraft II environments.
Value function factorization methods are commonly used in cooperative multi-agent reinforcement learning, with QMIX receiving significant attention. Many QMIX-based methods introduce monotonicity constraints between the joint action value and individual action values to achieve decentralized execution. However, such constraints limit the representation capacity of value factorization, restricting the joint action values it can represent and hindering the learning of the optimal policy. To address this challenge, we propose the Potentially Optimal Joint Actions Weighted QMIX (POWQMIX) algorithm, which recognizes the potentially optimal joint actions and assigns higher weights to the corresponding losses of these joint actions during training. We theoretically prove that with such a weighted training approach the optimal policy is guaranteed to be recovered. Experiments in matrix games, difficulty-enhanced predator-prey, and StarCraft II Multi-Agent Challenge environments demonstrate that our algorithm outperforms the state-of-the-art value-based multi-agent reinforcement learning methods.