Back to Results
First PageMeta Content
Dynamic programming / Stochastic control / Markov models / Operations research / Markov decision process / Reinforcement learning / Recurrent neural network / Statistics / Control theory / Markov processes


Two stochastic dynamic programming problems by model-free actor-critic recurrent-network learning in non-Markovian settings Eiji Mizutani Stuart E. Dreyfus
Add to Reading List

Document Date: 2008-07-16 21:59:54


Open Document

File Size: 103,86 KB

Share Result on Facebook

City

Addison-Wesley / Kobe / Belmont / /

Company

Princeton University Press / Neural Networks / Academic Press Inc. / MIT Press / Actor-Critic Elman Networks / Dynamic Recurrent Neural Networks / Hertz / /

Country

Japan / Jordan / Australia / /

/

Facility

Prentice Hall / University of New South Wales / University of Rochester / Operations Research University of California / Massachusetts Institute of Technology / /

IndustryTerm

path network / recurrent networks / reinforcement-learning type algorithm / recurrent network / /

Organization

University of New South Wales / Sydney / World Congress / Machine Intelligence / School of Computer Science and Engineering / Learning and Machine Intelligence / Princeton University / University of California / Berkeley / Operations Research University / Massachusetts Institute of Technology / University of Rochester / U.S. Securities and Exchange Commission / Computational Intelligence / Eiji Mizutani Stuart E. Dreyfus Department of Computer Science Tsing Hua University Hsinchu / /

Person

John N. Tsitsiklis / Andrew G. Barto / Hence / Long-Ji Lin / Richard S. Sutton / Stuart E. Dreyfus / Paul J. Werbos / Fernando Mark Pendrith / Eiji Mizutani / Steven D. Whitehead / Dimtri P. Bertsekas / Averill M. Law / Barak A. Pearlmutter / Eiji Mizutani Stuart / /

Position

baseball outfielder / Actor / Critic and Actor / Critic / /

ProgrammingLanguage

K / /

ProvinceOrState

New South Wales / Massachusetts / /

Region

South Wales / /

Technology

neural network / reinforcement-learning type algorithm / simulation / classical backward DP-algorithm / classical DP algorithm / DP algorithm / AClearning algorithm / /

URL

http /

SocialTag