This two-part paper introduces theoretical foundations and algorithms for continuous-time Q-learning in mean-field control with common noise. Part I establishes the theoretical framework, defining an integrated Q-function (Iq-function) and deriving conditions for optimal policies as fixed points. Part II builds upon this by devising Q-learning algorithms, including an Actor-Critic approach, and demonstrating their convergence and performance in linear-quadratic and other settings. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Introduces novel Q-learning algorithms for complex control problems, potentially advancing reinforcement learning applications in multi-agent systems.
RANK_REASON This is a research paper published on arXiv detailing theoretical foundations and algorithms for a specific type of control problem.