A finite time analysis of distributed Q-learning

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 of O( \1^2t_mix(1-)^6 d_^4 ,1||||(1-_2(W))(1-)^4 d_^3 \) under tabular lookup

Tasks

Reproductions