Back to Results
First PageMeta Content
Structure / Markov decision process / Q-learning / Model theory / Statistics / Mathematics / Reinforcement learning


Accelerating reinforcement learning by reusing abstract policies Yannick Plaino Bergamo 1 , Tiago Matos 1 , Valdinei Freire da Silva 1 , Anna Helena Reali Costa 1 1 Laboratório de Técnicas Inteligentes (LTI/EPUSP)
Add to Reading List

Document Date: 2012-04-05 12:47:26

Open Document

File Size: 290,60 KB

Share Result on Facebook

City

Berlin / /

Company

BP / /

Country

Brazil / /

/

IndustryTerm

depth-first search / learning algorithm / account existing solutions / /

Person

Horn Clauses / Paulo São Paulo / Anna Helena Reali Costa / /

Position

rt / teacher / discounted rewards Rt / function Rt / /

PublishedMedium

Journal of Artificial Intelligence Research / Lecture Notes in Computer Science / /

Technology

learning algorithm / TILDE algorithm / artificial intelligence / /

SocialTag