Back to Results
First PageMeta Content
Convex optimization / Mathematical optimization / Number theory / Topological groups / Markov decision process / Linear programming / Reinforcement learning / Representation theory / Μ operator / Mathematics / Algebra / Operations research


Stable Dual Dynamic Programming Tao Wang Daniel Lizotte Michael Bowling Dale Schuurmans Department of Computing Science
Add to Reading List

Document Date: 2007-10-21 19:53:48


Open Document

File Size: 139,09 KB

Share Result on Facebook

Company

P. Since O / MIT Press / The star / O. Unfortunately / /

Currency

pence / /

/

Event

Product Recall / Product Issues / /

Facility

Computing Science University of Alberta / Stable Dual Dynamic Programming Tao Wang Daniel Lizotte Michael Bowling Dale Schuurmans Department / /

IndustryTerm

update operator / target solution / mountain car domain / projection operator / primal algorithm / on-policy algorithms / matrix product / off-policy algorithms / equivalent solutions / mountain car problem / dynamic programming algorithms / primal and dual algorithms / dual dynamic programming algorithms / dual representation algorithms / classical algorithms / computing / on-policy operator / /

Organization

MIT / Stable Dual Dynamic Programming Tao Wang Daniel Lizotte Michael Bowling Dale Schuurmans Department / University of Alberta / /

Person

P . Let / B. Van Roy / Tsitsiklis Roy / Van Roy / J. Tsitsiklis / Michael Bowling Dale Schuurmans / /

Position

Prime Minister / transition model / rt / representative / However update PM / /

Product

Projection Operator / /

ProvinceOrState

Ohio / /

PublishedMedium

Machine Learning / /

Technology

dual representation algorithms / twelve algorithms / primal and dual algorithms / classical algorithms / dynamic programming algorithms / dual algorithms / dual dynamic programming algorithms / dual algorithm / corresponding primal algorithm / RL algorithms / on-policy algorithms / Machine Learning / off-policy algorithms / 4 DP algorithms / /

SocialTag