{"id":"https://openalex.org/W2585656226","doi":null,"title":"Algorithm selection of off-policy reinforcement learning algorithm.","display_name":"Algorithm selection of off-policy reinforcement learning algorithm.","publication_year":2017,"publication_date":"2017-01-30","ids":{"openalex":"https://openalex.org/W2585656226","mag":"2585656226"},"language":"en","primary_location":{"id":"mag:2585656226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1701.08810","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1701.08810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089214987","display_name":"Romain Laroche","orcid":"https://orcid.org/0000-0001-7180-2746","observed_orcids":["https://orcid.org/0000-0001-7180-2746"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Laroche","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7180-2746","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018329449","display_name":"Rapha\u00ebl F\u00e9raud","orcid":"https://orcid.org/0000-0001-9986-8878","observed_orcids":["https://orcid.org/0000-0001-9986-8878"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rapha\u00ebl F\u00e9raud","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9986-8878","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8730000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8730000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.12399999797344208,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/algorithm-selection","display_name":"algorithm selection","score":0.8849999904632568},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.984000027179718},{"id":"https://openalex.org/keywords/meta-algorithms","display_name":"meta-algorithms","score":0.7850000262260437},{"id":"https://openalex.org/keywords/stochastic-multi-armed-bandits","display_name":"stochastic bandits","score":0.746999979019165},{"id":"https://openalex.org/keywords/dialogue-systems","display_name":"dialogue systems","score":0.7020000219345093},{"id":"https://openalex.org/keywords/negotiation-dialogue","display_name":"negotiation dialogue","score":0.5979999899864197},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9111514091491699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244451642036438},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5498150587081909},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.544892430305481},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49348509311676025},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4810231328010559},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.473225474357605},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4504458010196686},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4416506588459015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375036060810089},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41411054134368896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1480778455734253},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.10329663753509521},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2585656226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1701.08810","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2585656226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1701.08810","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W30493077","https://openalex.org/W52170320","https://openalex.org/W119157355","https://openalex.org/W192920577","https://openalex.org/W200223693","https://openalex.org/W1495775210","https://openalex.org/W1601974704","https://openalex.org/W1757796397","https://openalex.org/W1861050369","https://openalex.org/W1925875298","https://openalex.org/W1977474365","https://openalex.org/W1996579288","https://openalex.org/W2029514605","https://openalex.org/W2038372264","https://openalex.org/W2043806097","https://openalex.org/W2077902449","https://openalex.org/W2089213632","https://openalex.org/W2117012949","https://openalex.org/W2120346334","https://openalex.org/W2126405658","https://openalex.org/W2132622533","https://openalex.org/W2141839844","https://openalex.org/W2145339207","https://openalex.org/W2147148915","https://openalex.org/W2149476049","https://openalex.org/W2150468603","https://openalex.org/W2158984235","https://openalex.org/W2163068732","https://openalex.org/W2168405694","https://openalex.org/W2185566361","https://openalex.org/W2250891614","https://openalex.org/W2257979135","https://openalex.org/W2273762088","https://openalex.org/W2280163991","https://openalex.org/W2295986874","https://openalex.org/W2397581010","https://openalex.org/W2399299813","https://openalex.org/W2407709678","https://openalex.org/W2410985346","https://openalex.org/W2468710617","https://openalex.org/W2550182557","https://openalex.org/W2562912037","https://openalex.org/W2577408049","https://openalex.org/W2578390274","https://openalex.org/W2730850385","https://openalex.org/W2738835553","https://openalex.org/W2914775474","https://openalex.org/W3011120880","https://openalex.org/W3100895096"],"related_works":["https://openalex.org/W2739415903","https://openalex.org/W2721507161","https://openalex.org/W2783634529","https://openalex.org/W2528481956","https://openalex.org/W2266890668","https://openalex.org/W4298306847","https://openalex.org/W4389421231","https://openalex.org/W4299126605","https://openalex.org/W6978124148","https://openalex.org/W7100622596"],"abstract_inverted_index":{"Dialogue":[0],"systems":[1],"rely":[2],"on":[3,175],"a":[4,66,110,134,147,168,176],"careful":[5],"reinforcement":[6,56,72],"learning":[7,10,57,73],"design:":[8],"the":[9,23,32,42,45,51,79,88,94,97,105,125,141,155,165,183,187,198,202,206],"algorithm":[11,58,86,142,188,200],"and":[12,39,131],"its":[13,27,152],"state":[14],"space":[15],"representation.":[16],"In":[17,35],"lack":[18],"of":[19,44,53,69,81,93,140,170,186],"more":[20],"rigorous":[21],"knowledge,":[22],"designer":[24],"resorts":[25],"to":[26,30,37,40,103,123,132,164],"practical":[28,184],"experience":[29],"choose":[31],"best":[33,199],"option.":[34],"order":[36,102],"automate":[38],"improve":[41],"performance":[43],"aforementioned":[46,207],"process,":[47],"this":[48],"article":[49,108],"formalises":[50],"problem":[52],"online":[54],"off-policy":[55,71],"selection.":[59,143],"A":[60],"meta-algorithm":[61],"is":[62,90,122,162],"given":[63],"for":[64,190],"input":[65],"portfolio":[67,89],"constituted":[68],"several":[70],"algorithms.":[74],"It":[75],"then":[76],"determines":[77],"at":[78,128],"beginning":[80],"each":[82,129],"new":[83],"trajectory,":[84,100],"which":[85],"in":[87,91,101,138,167,193,201],"control":[92],"behaviour":[95],"during":[96],"full":[98],"next":[99],"maximise":[104],"return.":[106],"The":[107,180],"presents":[109],"novel":[111],"meta-algorithm,":[112],"called":[113],"Epochal":[114],"Stochastic":[115],"Bandit":[116],"Algorithm":[117],"Selection":[118],"(ESBAS).":[119],"Its":[120],"principle":[121],"freeze":[124],"policy":[126],"updates":[127],"epoch,":[130],"leave":[133],"rebooted":[135],"stochastic":[136],"bandit":[137],"charge":[139],"Under":[144],"some":[145],"assumptions,":[146],"thorough":[148],"theoretical":[149],"analysis":[150],"demonstrates":[151],"near-optimality":[153],"considering":[154],"structural":[156],"sampling":[157],"budget":[158],"limitations.":[159],"Then,":[160],"ESBAS":[161],"put":[163],"test":[166],"set":[169],"experiments":[171],"with":[172],"various":[173],"portfolios,":[174],"negotiation":[177],"dialogue":[178,191],"game.":[179],"results":[181],"show":[182],"benefits":[185],"selection":[189],"systems,":[192],"most":[194],"cases":[195],"even":[196,204],"outperforming":[197],"portfolio,":[203],"when":[205],"assumptions":[208],"are":[209],"transgressed.":[210]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2017-02-10T00:00:00"}