On Convergence of Emphatic Temporal-Difference Learning
published: Aug. 20, 2015, recorded: July 2015, views: 101
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White as an improved solution to the problem of divergence of off-policy temporal-difference learning with linear function approximation. We present in this paper the first convergence proofs for two emphatic algorithms, ETD($\lambda$) and ELSTD($\lambda$). We prove, under general off-policy conditions, the convergence in $L^1$ for ELSTD($\lambda$) iterates and the almost sure convergence of the approximate value functions calculated by both algorithms. Our analysis involves new techniques with applications beyond emphatic algorithms leading, for example, to the first proof that standard TD($\lambda$) also converges under off-policy training for $\lambda$ sufficiently large.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !