EE365: Dynamic Programming Proof 1 Markov decision problem find policy µ = (µ0 , . . . , µT −1 ) that minimizes

First Page		Document Content
Date: 2016-01-08 18:51:40		EE365: Dynamic Programming Proof 1 Markov decision problem find policy µ = (µ0 , . . . , µT −1 ) that minimizes Add to Reading List Source URL: ee266.stanford.edu Download Document from Source Website File Size: 134,92 KB Share Document on Facebook