Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations Timothy A. Mann MANN @ EE . TECHNION . AC . IL Shie Mannor SHIE @ EE . TECHNION . AC . IL

First Page		Document Content
Date: 2014-02-16 19:30:21 Markov processes Stochastic control Operations research Mathematical sciences Analytic number theory Markov decision process Reinforcement learning Mathematical optimization Prime-counting function Statistics Control theory Dynamic programming		Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations Timothy A. Mann MANN @ EE . TECHNION . AC . IL Shie Mannor SHIE @ EE . TECHNION . AC . IL Add to Reading List Source URL: jmlr.org Download Document from Source Website File Size: 580,22 KB Share Document on Facebook

	Adv Comput Math:55–70 DOIs10444The prime-counting function and its analytic approximations π(x) and its approximations DocID: 1rJq4 - View Document
	SMOOTH NUMBERS AND THE QUADRATIC SIEVE Carl Pomerance When faced with a large number n to factor, what do you do first? You might say “Look at the last digit,” with the idea of cheaply pulling out possible factors of DocID: 1rfno - View Document
	Stochastic Optimal Policies when the Discount Rate Vanishes ? Kazuo Nishimura Institute of Economic Research, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto, Japan DocID: 1qjbB - View Document
	INTEGERS: ELECTRONIC JOURNAL OF COMBINATORIAL NUMBER THEORY), #A31 ON THE IRRATIONALITY OF A DIVISOR FUNCTION SERIES John B. Friedlander1 Department of Mathematics, University of Toronto, Toronto, Ontario M5S 3G DocID: 1pEOX - View Document
	Precise asymptotics of the length spectrum for finite geometry Riemann surfaces By Fr´ ed´ eric Naud Abstract DocID: 1pDjb - View Document