{"id":"https://openalex.org/W3048454540","doi":"https://doi.org/10.1609/aaai.v35i8.16895","title":"Reinforcement Learning with Trajectory Feedback","display_name":"Reinforcement Learning with Trajectory Feedback","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3048454540","doi":"https://doi.org/10.1609/aaai.v35i8.16895","mag":"3048454540"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v35i8.16895","doi":"https://doi.org/10.1609/aaai.v35i8.16895","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i8.16895","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v35i8.16895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090891199","display_name":"Yonathan Efroni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]},{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yonathan Efroni","raw_affiliation_strings":["Microsoft Research, New York\nTechnion, Israel Institute of Technology","Technion \u2013 Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, New York\nTechnion, Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211","https://openalex.org/I4401726785"]},{"raw_affiliation_string":"Technion \u2013 Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018784842","display_name":"Nadav Merlis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nadav Merlis","raw_affiliation_strings":["Technion, Israel Institute of Technology","Technion \u2013 Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion \u2013 Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647","observed_orcids":["https://orcid.org/0000-0003-4439-7647"]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Technion, Israel Institute of Technology\nNvidia Research, Israel","Technion \u2013 Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Israel Institute of Technology\nNvidia Research, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion \u2013 Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9402,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77393362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"35","issue":"8","first_page":"7288","last_page":"7295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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":0.004000000189989805,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.8059999942779541},{"id":"https://openalex.org/keywords/partial-feedback","display_name":"partial feedback","score":0.5059999823570251},{"id":"https://openalex.org/keywords/reward-estimation","display_name":"reward estimation","score":0.6200000047683716},{"id":"https://openalex.org/keywords/least-squares-estimation","display_name":"least squares estimation","score":0.8899999856948853},{"id":"https://openalex.org/keywords/regret-analysis","display_name":"regret analysis","score":0.9269999861717224},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.7720000147819519},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.31200000643730164}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8323579430580139},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.792654275894165},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7496938109397888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6231271624565125},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.551939070224762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4455326199531555},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44138917326927185},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4309196472167969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3266872763633728},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21875447034835815},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10545197129249573},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06733882427215576},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v35i8.16895","doi":"https://doi.org/10.1609/aaai.v35i8.16895","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i8.16895","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2008.06036","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06036","pdf_url":"https://arxiv.org/pdf/2008.06036","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":null,"raw_type":"text"},{"id":"mag:3048454540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.06036.pdf","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},{"id":"doi:10.48550/arxiv.2008.06036","doi":"https://doi.org/10.48550/arxiv.2008.06036","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.06036","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v35i8.16895","doi":"https://doi.org/10.1609/aaai.v35i8.16895","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i8.16895","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048454540.pdf","grobid_xml":"https://content.openalex.org/works/W3048454540.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W21934178","https://openalex.org/W50486269","https://openalex.org/W1487320471","https://openalex.org/W1518931405","https://openalex.org/W1560153690","https://openalex.org/W1850488217","https://openalex.org/W1915973093","https://openalex.org/W1968018625","https://openalex.org/W1981276685","https://openalex.org/W2019029889","https://openalex.org/W2103715332","https://openalex.org/W2111764152","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2119738618","https://openalex.org/W2145339207","https://openalex.org/W2150234726","https://openalex.org/W2160163723","https://openalex.org/W2166253248","https://openalex.org/W2470693974","https://openalex.org/W2518564545","https://openalex.org/W2555558374","https://openalex.org/W2585536612","https://openalex.org/W2604884452","https://openalex.org/W2766447205","https://openalex.org/W2899637793","https://openalex.org/W2907502549","https://openalex.org/W2944264312","https://openalex.org/W2946284958","https://openalex.org/W2947223001","https://openalex.org/W2948080528","https://openalex.org/W2952585682","https://openalex.org/W2963049774","https://openalex.org/W2963582321","https://openalex.org/W2963603291","https://openalex.org/W2964054583","https://openalex.org/W2964161785","https://openalex.org/W2964986650","https://openalex.org/W2970770768","https://openalex.org/W2970870329","https://openalex.org/W2971249033","https://openalex.org/W2991935368","https://openalex.org/W3037983390","https://openalex.org/W3046626913","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W3170379366","https://openalex.org/W2576787642","https://openalex.org/W4407184986","https://openalex.org/W4391549745","https://openalex.org/W3102886701","https://openalex.org/W4414588448","https://openalex.org/W3213126186","https://openalex.org/W7220970510","https://openalex.org/W4415795636","https://openalex.org/W2295496969"],"abstract_inverted_index":{"The":[0],"standard":[1],"feedback":[2,27],"model":[3,118,136],"of":[4,11,48,58,77,88,107,124],"reinforcement":[5,97],"learning":[6,98],"requires":[7],"revealing":[8],"the":[9,22,60,75,78,83,86,108,113,122,134],"reward":[10,61],"every":[12,64],"visited":[13],"state-action":[14],"pair.":[15],"However,":[16],"in":[17,148],"practice,":[18],"it":[19],"is":[20,28,137],"often":[21],"case":[23],"that":[24,73,146],"such":[25],"frequent":[26],"not":[29],"available.":[30],"In":[31],"this":[32,41,93,101],"work,":[33],"we":[34,51,66,68,139],"take":[35],"a":[36,45,71,141,149],"first":[37],"step":[38],"towards":[39],"relaxing":[40],"assumption":[42],"and":[43,115,120],"require":[44],"weaker":[46],"form":[47],"feedback,":[49],"which":[50],"refer":[52],"to":[53,100],"as":[54],"\\emph{trajectory":[55],"feedback}.":[56],"Instead":[57],"observing":[59],"obtained":[62,91],"after":[63],"action,":[65],"assume":[67],"only":[69],"receive":[70],"score":[72],"represents":[74],"quality":[76],"whole":[79],"trajectory":[80],"observed":[81],"by":[82,127],"agent,":[84],"namely,":[85],"sum":[87],"all":[89],"rewards":[90],"over":[92],"trajectory.":[94],"We":[95],"extend":[96],"algorithms":[99,126],"setting,":[102],"based":[103],"on":[104],"least-squares":[105],"estimation":[106],"unknown":[109,116],"reward,":[110],"for":[111],"both":[112],"known":[114],"transition":[117,135],"cases,":[119],"study":[121],"performance":[123],"these":[125],"analyzing":[128],"their":[129],"regret.":[130],"For":[131],"cases":[132],"where":[133],"unknown,":[138],"offer":[140],"hybrid":[142],"optimistic-Thompson":[143],"Sampling":[144],"approach":[145],"results":[147],"tractable":[150],"algorithm.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-08-18T00:00:00"}