A Finite-Time Analysis of Distributed Q-Learning

Han-Dong Lim, Donghwan Lee; 6:165−200, 2025.

Presented at the Reinforcement Learning Conference (RLC), Edmonton, Alberta, Canada, August 5–9, 2025.

Abstract

Multi-agent reinforcement learning (MARL) has witnessed a remarkable surge in interest, fueled by the empirical success achieved in applications of single-agent reinforcement learning (RL). In this study, we consider a distributed Q-learning scenario, wherein a number of agents cooperatively solve a sequential decision making problem without access to the central reward function which is an average of the local rewards. In particular, we study finite-time analysis of a distributed Q-learning algorithm, and provide a new sample complexity result under tabular lookup setting for Markovian observation model.

[abs][pdf]

BibTeX

@article{lim2025finite,
    title={A Finite-Time Analysis of Distributed {Q-Learning}},
    author={Lim, Han-Dong and Lee, Donghwan},
    journal={Reinforcement Learning Journal},
    volume={6},
    pages={165--200},
    year={2025}
}