Reinforcement Learning: A Survey

by: Leslie P Kaelbling, Michael L Littman, Andrew P Moore

Journal of Artificial Intelligence Research, Vol. 4 (1996), pp. 237-285.

View FullText article

CiteSeer (at Penn State), CiteSeer (at MIT), CiteSeer (at Zurich), CiteSeer (at Singapore), http://www.cs.cmu.edu/afs/cs/project/jair…, http://citeseer.ist.psu.edu/kaelbling96re…

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

KurtSteinkraus, eldan, unnonouno, dep, vaasu, cyph3r, davidmihalcik, craigtalbert, damcci, hllee, lop, afoerster, gagliol, sugarexpletive, mzygmunt, dowlingj, josepe, docB, Glimcher_Lab (group), Netmob (group), P2P (group), SensorNetworks (group), kickOffTUG-Robocup (group), bach, tdahl, Tominator

Find related articles with these CiteULike tags

1995, 2006, action_selection, ai, bandit, computer_science, dopamine, learning, machine-learning, misc, ml, neuroscience, no-tag, reinforcement, reinforcementlearning, reinforcement_learning, reinforcement-learning, reinforcment, rl, robocup, survey, theory

摘要

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of currentwork are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in...

@article{Kaelbling1996Reinforcement, abstract = {This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of currentwork are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in...}, author = {Kaelbling, Leslie P. and Littman, Michael L. and Moore, Andrew P. }, citeulike-article-id = {4578}, journal = {Journal of Artificial Intelligence Research}, keywords = {bandit, reinforcement-learning}, pages = {237--285}, posted-at = {2006-08-21 17:44:12}, priority = {0}, title = {Reinforcement Learning: A Survey}, url = {http://citeseer.ist.psu.edu/kaelbling96reinforcement.html}, volume = {4}, year = {1996} }

RIS record

TY - JOUR ID - Kaelbling1996Reinforcement L3 - citeulike-article-id:4578 TI - Reinforcement Learning: A Survey JF - Journal of Artificial Intelligence Research VL - 4 SP - 237 EP - 285 N2 - This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of currentwork are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in... KW - bandit KW - reinforcement-learning AU - Kaelbling, Leslie AU - Littman, Michael AU - Moore, Andrew PY - 1996/// UR - http://citeseer.ist.psu.edu/kaelbling96reinforcement.html ER -

RIS BibTeX