Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning

Abstract

Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise. When agents share a common reward, the actions of all N agents jointly determine each agent's learning signal, so cross-agent noise grows with N. In the policy gradient setting, per-agent gradient estimate variance scales as Θ(N), yielding sample complexity O(N/ε). We observe that many domains, including cloud computing, transportation, and power systems, have differentiable analytical models that prescribe efficient system states. In this work, we propose Descent-Guided Policy Gradient (DG-PG), a framework that utilizes these analytical models to provide each agent with a noise-free gradient signal, decoupling each agent's gradient from the actions of all others. We prove that DG-PG reduces gradient variance from Θ(N) to O(1), preserves the equilibria of the cooperative game, and achieves agent-independent sample complexity O(1/ε). On a heterogeneous cloud scheduling task with up to 200 agents, DG-PG converges within 10 episodes at every tested scale, from N=5 to N=200, directly confirming the predicted scale-invariant complexity, while MAPPO and IPPO fail to converge under identical architectures.

Reproductions