Back to Results
First PageMeta Content
Systems theory / Equations / Mathematical optimization / SARSA / Q-learning / Markov processes / Stochastic control / Reinforcement learning / Markov decision process / Statistics / Control theory / Dynamic programming


Q-Decomposition for Reinforcement Learning Agents Stuart Russell @.. Andrew L. Zimdars @..
Add to Reading List

Document Date: 2003-06-03 00:44:40

Open Document

File Size: 122,54 KB

Share Result on Facebook

City

San Mateo / Belmont / Bled / Seattle / Washington DC / Stockholm / /

Company

Neural Information Processing Systems / MIT Artificial Intelligence Laboratory / Autonomous Systems / /

Country

Slovenia / United Kingdom / /

Currency

USD / /

Facility

University of California / University of Cambridge / /

IndustryTerm

local utilities / reinforcement learning algorithm / cooperative multiagent systems / connectionist systems / communications requirements / conditional utilities / /

Organization

Cambridge University Engineering Department / Computer Science Division / Cambridge University / University of Cambridge / MIT / Board of Canada / University of California / Berkeley / /

Person

Stuart Russell / Andrew L. Zimdars / Morgan Kaufmann / /

Position

supervisor / arbitrator / central arbitrator for action selection / single racer / bishop / fisheries commissioner / central arbitrator / race car driver / racer / /

ProvinceOrState

California / Massachusetts / /

PublishedMedium

Machine Learning / Journal of Artificial Intelligence Research / /

Technology

Sarsa algorithms / neural network / artificial intelligence / conventional Q-learning algorithm / Sarsa reinforcement learning algorithm / Sarsa algorithm / Machine Learning / /

SocialTag