Interactively shaping agents via human reinforcement: the TAMER framework. Knox, W B. & Stone, P. ACM, New York, New York, USA, 2009. abstract bibtex Abstract As computational learning agents move into domains that incur real costs (eg, autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample.
@Book{Knox2009,
author = {Knox, W Bradley and Stone, Peter},
title = {Interactively shaping agents via human reinforcement: the TAMER framework},
volume = {},
pages = {9-16},
editor = {},
publisher = {ACM},
address = {New York, New York, USA},
year = {2009},
abstract = {Abstract As computational learning agents move into domains that incur real costs (eg, autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample.},
keywords = {}}
Downloads: 0
{"_id":"CqqeR6guqCQFGECNk","bibbaseid":"knox-stone-interactivelyshapingagentsviahumanreinforcementthetamerframework-2009","authorIDs":[],"author_short":["Knox, W B.","Stone, P."],"bibdata":{"bibtype":"book","type":"book","author":[{"propositions":[],"lastnames":["Knox"],"firstnames":["W","Bradley"],"suffixes":[]},{"propositions":[],"lastnames":["Stone"],"firstnames":["Peter"],"suffixes":[]}],"title":"Interactively shaping agents via human reinforcement: the TAMER framework","volume":"","pages":"9-16","editor":[{"firstnames":[],"propositions":[],"lastnames":[""],"suffixes":[]}],"publisher":"ACM","address":"New York, New York, USA","year":"2009","abstract":"Abstract As computational learning agents move into domains that incur real costs (eg, autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample.","keywords":"","bibtex":"@Book{Knox2009,\nauthor = {Knox, W Bradley and Stone, Peter}, \ntitle = {Interactively shaping agents via human reinforcement: the TAMER framework}, \nvolume = {}, \npages = {9-16}, \neditor = {}, \npublisher = {ACM}, \naddress = {New York, New York, USA}, \nyear = {2009}, \nabstract = {Abstract As computational learning agents move into domains that incur real costs (eg, autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample.}, \nkeywords = {}}\n\n","author_short":["Knox, W B.","Stone, P."],"editor_short":[""],"key":"Knox2009","id":"Knox2009","bibbaseid":"knox-stone-interactivelyshapingagentsviahumanreinforcementthetamerframework-2009","role":"author","urls":{},"downloads":0},"bibtype":"book","biburl":"https://gist.githubusercontent.com/stuhlmueller/a37ef2ef4f378ebcb73d249fe0f8377a/raw/6f96f6f779501bd9482896af3e4db4de88c35079/references.bib","creationDate":"2020-01-27T02:13:34.484Z","downloads":0,"keywords":[],"search_terms":["interactively","shaping","agents","via","human","reinforcement","tamer","framework","knox","stone"],"title":"Interactively shaping agents via human reinforcement: the TAMER framework","year":2009,"dataSources":["hEoKh4ygEAWbAZ5iy"]}