OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHS

PDF Publication Title:

OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHS ( optimizing-expectations-from-deep-reinforcement-learning-to- )

Previous Page View | Next Page View | Return to Search List

Text from PDF Page: 004

ACKNOWLEDGMENTS All of the work described in this thesis was done in collaboration with my advisor, Pieter Abbeel, who has continually pointed me in the right direction and provided inspiration to do the best work I could. I’d also like to thank Sergey Levine and Philipp Moritz, who were my closest collabo- rators on the main work in the thesis, and with whom I shared many great conversations. The work on stochastic computation graphs grew out of discussions with my coauthors Pieter Abbeel, Nick Heess, and Theophane Weber. Thanks to Mike Jordan, Stuart Russell, and Joan Bruna for serving on my quals and thesis committee, and for many insightful conversations over the past few years. I also collaborated with a number of colleagues at Berkeley on several projects that are not included in this thesis document, including Jonathan Ho, Alex Lee, Sachin Patil, Zoe McCarthy, Greg Kahn, Michael Laskey, Ibrahim Awwal, Henry Bradlow, Jia Pan, Cameron Lee, Ankush Gupta, Sibi Venkatesan, Mal- lory Tayson-Frederick, and Yan Duan. I am thankful to DeepMind for giving me the opportunity to do an internship there in the Spring of 2015, so I would like to thank my supervisor, David Silver, as well as Yuval Tassa, Greg Wayne, Tom Erez, and Tim Lillicrap. Thanks to UC Berkeley for being flexible and allowing me to switch from the neuro- science program to the computer science program without much difficulty. Thanks to the wonderful staff at Philz Coffee in Berkeley, where most of the research and writing was performed, along with Brewed Awakening, Nefeli’s, Strada, and Asha Tea House. Finally, this thesis is dedicated to my parents, for all the years of love and support, and for doing so much to further my education. 2

PDF Image | OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHS

PDF Search Title:

OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHS

Original File Name Searched:

thesis-optimizing-deep-learning.pdf

DIY PDF Search: Google It | Yahoo | Bing

Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info

Cruising Review Topics and Articles More Info

Software based on Filemaker for the travel industry More Info

The Burgenstock Resort: Reviews on CruisingReview website... More Info

Resort Reviews: World Class resorts... More Info

The Riffelalp Resort: Reviews on CruisingReview website... More Info

CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com (Standard Web Page)