`

Timezone: »

 
Poster
Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis
Shaocong Ma · Yi Zhou · Shaofeng Zou

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #95
Variance reduction techniques have been successfully applied to temporal-difference (TD) learning and help to improve the sample complexity in policy evaluation. However, the existing work applied variance reduction to either the less popular one time-scale TD algorithm or the two time-scale GTD algorithm but with a finite number of i.i.d.\ samples, and both algorithms apply to only the on-policy setting. In this work, we develop a variance reduction scheme for the two time-scale TDC algorithm in the off-policy setting and analyze its non-asymptotic convergence rate over both i.i.d.\ and Markovian samples. In the i.i.d setting, our algorithm achieves an improved sample complexity $\calO(\epsilon^{-\frac{3}{5}} \log{\epsilon}^{-1})$ over the state-of-the-art result $\calO(\epsilon^{-1} \log {\epsilon}^{-1})$. In the Markovian setting, our algorithm achieves the state-of-the-art sample complexity $\calO(\epsilon^{-1} \log {\epsilon}^{-1})$ that is near-optimal. Experiments demonstrate that the proposed variance-reduced TDC achieves a smaller asymptotic convergence error than both the conventional TDC and the variance-reduced TD.

Author Information

Shaocong Ma (University of Utah)
Yi Zhou (University of Utah)
Shaofeng Zou (University at Buffalo, the State University of New York)

More from the Same Authors