Video: Ashkan Ertefaie, "A Greedy Gradient Q-learning Approach for Constructing Optimal Policies in Infinite Time Horizon Settings"

Video From 18w5054: Workshop on the Interface of Machine Learning and Statistical Inference

Ashkan Ertefaie, University of Rochester

Thursday, January 18, 2018 16:43 - 17:14

A Greedy Gradient Q-learning Approach for Constructing Optimal Policies in Infinite Time Horizon Settings

Ashkan Ertefaie, Video: A Greedy Gradient Q-learning Approach for Constructing Optimal Policies in Infinite Time Horizon Settings

Ashkan Ertefaie, A Greedy Gradient Q-learning Approach for Constructing Optimal Policies in Infinite Time Horizon Settings, Workshop on the Interface of Machine Learning and Statistical Inference, BIRS, BIRS talk, 18w5054, math, mathematics, video

Banff International Research Station

presentation

mpeg4

99M

http://www.birs.ca/events/2018/5-day-workshops/18w5054/videos

http://www.birs.ca/events/2018/5-day-workshops/18w5054/videos/watch/201801181643-Ertefaie.html

Download this video (99M)