Convergence Results for Single-Step On-Policy Reinforcement Learning Algorithms. Singh, S., Jaakkola, T., Littman, M. L., & Szepesvári, C. Machine Learning, 1998. To appearbibtex @article{singh-jaak-littman-sze:ml98,
Author = {Satinder Singh and Tommi Jaakkola and Michael L. Littman and Csaba Szepesv\'{a}ri},
Journal = {Machine Learning},
Note = {To appear},
Title = {Convergence Results for Single-Step On-Policy Reinforcement Learning Algorithms},
Year = {1998}}
Downloads: 0
{"_id":"pcCNssbyFnF6ZDCf6","bibbaseid":"singh-jaakkola-littman-szepesvri-convergenceresultsforsinglesteponpolicyreinforcementlearningalgorithms-1998","downloads":0,"creationDate":"2015-12-09T07:08:17.814Z","title":"Convergence Results for Single-Step On-Policy Reinforcement Learning Algorithms","author_short":["Singh, S.","Jaakkola, T.","Littman, M. L.","Szepesvári, C."],"year":1998,"bibtype":"article","biburl":"http://www.cs.toronto.edu/cogs/bib/standard-long.bib","bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Satinder"],"propositions":[],"lastnames":["Singh"],"suffixes":[]},{"firstnames":["Tommi"],"propositions":[],"lastnames":["Jaakkola"],"suffixes":[]},{"firstnames":["Michael","L."],"propositions":[],"lastnames":["Littman"],"suffixes":[]},{"firstnames":["Csaba"],"propositions":[],"lastnames":["Szepesvári"],"suffixes":[]}],"journal":"Machine Learning","note":"To appear","title":"Convergence Results for Single-Step On-Policy Reinforcement Learning Algorithms","year":"1998","bibtex":"@article{singh-jaak-littman-sze:ml98,\n\tAuthor = {Satinder Singh and Tommi Jaakkola and Michael L. Littman and Csaba Szepesv\\'{a}ri},\n\tJournal = {Machine Learning},\n\tNote = {To appear},\n\tTitle = {Convergence Results for Single-Step On-Policy Reinforcement Learning Algorithms},\n\tYear = {1998}}\n\n","author_short":["Singh, S.","Jaakkola, T.","Littman, M. L.","Szepesvári, C."],"key":"singh-jaak-littman-sze:ml98","id":"singh-jaak-littman-sze:ml98","bibbaseid":"singh-jaakkola-littman-szepesvri-convergenceresultsforsinglesteponpolicyreinforcementlearningalgorithms-1998","role":"author","urls":{},"downloads":0,"html":""},"search_terms":["convergence","results","single","step","policy","reinforcement","learning","algorithms","singh","jaakkola","littman","szepesvári"],"keywords":[],"authorIDs":[],"dataSources":["2cjnbEWxd35GBeqEe"]}