A finite time analysis of distributed Q-learning

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 $Õ( min\{1/ε^2{tₘᵢₓ}{(1-γ)^6 dₘᵢₙ^4 } ,1/ε{√||||}{(1-σ_2(W))(1-γ)^4 dₘᵢₙ^3} \})$ under tabular lookup