Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity
This work addresses sample efficiency for off-policy optimal control in reinforcement learning, representing an incremental improvement over existing methods.
The paper tackles the high sample complexity of the Greedy-GQ reinforcement learning algorithm by proposing a variance-reduced version (VR-Greedy-GQ), which reduces the sample complexity from O(ε^{-3}) to O(ε^{-2}) under linear function approximation and Markovian sampling.
Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under linear function approximation and Markovian sampling, and the algorithm is shown to achieve an $ε$-stationary point with a sample complexity in the order of $\mathcal{O}(ε^{-3})$. Such a high sample complexity is due to the large variance induced by the Markovian samples. In this paper, we propose a variance-reduced Greedy-GQ (VR-Greedy-GQ) algorithm for off-policy optimal control. In particular, the algorithm applies the SVRG-based variance reduction scheme to reduce the stochastic variance of the two time-scale updates. We study the finite-time convergence of VR-Greedy-GQ under linear function approximation and Markovian sampling and show that the algorithm achieves a much smaller bias and variance error than the original Greedy-GQ. In particular, we prove that VR-Greedy-GQ achieves an improved sample complexity that is in the order of $\mathcal{O}(ε^{-2})$. We further compare the performance of VR-Greedy-GQ with that of Greedy-GQ in various RL experiments to corroborate our theoretical findings.