PulseAugur
LIVE 08:06:09
research · [2 sources] ·
0
research

Researchers develop continuous-time q-learning for mean-field control with common noise

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.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Zhenjie Ren, Xiaoli Wei, Xiang Yu, Xun Yu Zhou ·

    Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations

    arXiv:2604.27372v1 Announce Type: cross Abstract: This paper investigates the continuous-time counterpart of the Q-function for entropy-regularized mean-field control (MFC) with controlled common noise, coined as q-function by Jia and Zhou (2023) in the single agent's model. We f…

  2. arXiv cs.LG TIER_1 · Zhenjie Ren, Xiaoli Wei, Xiang Yu, Xun Yu Zhou ·

    Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms

    arXiv:2604.27378v1 Announce Type: cross Abstract: This paper is a continuation work of Ren et al. (2026) aiming to further devise q-learning algorithms for mean-field control (MFC) with controlled common noise. Based on the relaxed control formulation, we first establish the mart…