Timezone: »

A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods
Yue Wu · Weitong ZHANG · Pan Xu · Quanquan Gu

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #84
Actor-critic (AC) methods have exhibited great empirical success compared with other reinforcement learning algorithms, where the actor uses the policy gradient to improve the learning policy and the critic uses temporal difference learning to estimate the policy gradient. Under the two time-scale learning rate schedule, the asymptotic convergence of AC has been well studied in the literature. However, the non-asymptotic convergence and finite sample complexity of actor-critic methods are largely open. In this work, we provide a non-asymptotic analysis for two time-scale actor-critic methods under non-i.i.d. setting. We prove that the actor-critic method is guaranteed to find a first-order stationary point (i.e., $\|\nabla J(\bm{\theta})\|_2^2 \le \epsilon$) of the non-concave performance function $J(\bm{\theta})$, with $\mathcal{\tilde{O}}(\epsilon^{-2.5})$ sample complexity. To the best of our knowledge, this is the first work providing finite-time analysis and sample complexity bound for two time-scale actor-critic methods.

Author Information

Yue Wu (University of California, Los Angeles)
Weitong ZHANG (University of California, Los Angeles)
Pan Xu (University of California, Los Angeles)
Quanquan Gu (UCLA)

More from the Same Authors