{"id":"https://openalex.org/W2902854091","doi":null,"title":"Entropic Policy Composition with Generalized Policy Improvement and Divergence Correction.","display_name":"Entropic Policy Composition with Generalized Policy Improvement and Divergence Correction.","publication_year":2018,"publication_date":"2018-12-05","ids":{"openalex":"https://openalex.org/W2902854091","mag":"2902854091"},"language":"en","primary_location":{"id":"mag:2902854091","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1812.02216","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":"http://export.arxiv.org/pdf/1812.02216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086547450","display_name":"Jonathan J. Hunt","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan J. Hunt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008592589","display_name":"Andr\u00e9 da Motta Salles Barreto","orcid":"https://orcid.org/0000-0001-6168-6972","observed_orcids":["https://orcid.org/0000-0001-6168-6972"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Barreto","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6168-6972","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066294254","display_name":"Timothy Lillicrap","orcid":"https://orcid.org/0000-0001-8918-486X","observed_orcids":["https://orcid.org/0000-0001-8918-486X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Lillicrap","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256","observed_orcids":["https://orcid.org/0000-0001-7876-9256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Heess","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7876-9256","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":1,"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-composition","display_name":"policy composition","score":0.7570000290870667},{"id":"https://openalex.org/keywords/skill-transfer","display_name":"skill transfer","score":0.7009999752044678},{"id":"https://openalex.org/keywords/policy-divergence","display_name":"policy divergence","score":0.7360000014305115},{"id":"https://openalex.org/keywords/successor-features","display_name":"successor features","score":0.8889999985694885},{"id":"https://openalex.org/keywords/continuous-action-spaces","display_name":"continuous action spaces","score":0.902999997138977},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.5889999866485596},{"id":"https://openalex.org/keywords/action-value-function","display_name":"action-value function","score":0.6200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827550768852234},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7697089910507202},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.7642841339111328},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6065298318862915},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5485107898712158},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4971814453601837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4921988546848297},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46317535638809204},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45808637142181396},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4226807951927185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40642249584198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13226830959320068},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2902854091","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1812.02216","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:2902854091","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1812.02216","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1503398984","https://openalex.org/W1520048352","https://openalex.org/W1824523713","https://openalex.org/W1979985652","https://openalex.org/W2026659355","https://openalex.org/W2054265914","https://openalex.org/W2098774185","https://openalex.org/W2113885007","https://openalex.org/W2124215603","https://openalex.org/W2145339207","https://openalex.org/W2161905760","https://openalex.org/W2181409883","https://openalex.org/W2257979135","https://openalex.org/W2741442067","https://openalex.org/W2810785043","https://openalex.org/W2962717849"],"related_works":["https://openalex.org/W2909000816","https://openalex.org/W2804673281","https://openalex.org/W2996320348","https://openalex.org/W2854307805","https://openalex.org/W4226016088","https://openalex.org/W4399115143","https://openalex.org/W3196740181","https://openalex.org/W2945529113","https://openalex.org/W4407186295","https://openalex.org/W3008744627"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,151],"(RL)":[3],"algorithms":[4],"have":[5],"made":[6],"great":[7],"strides":[8],"in":[9,74,127,138,162,174],"recent":[10],"years.":[11],"An":[12],"important":[13],"remaining":[14],"challenge":[15],"is":[16,98,172],"the":[17,48,53,75,113,121,141,152,163],"ability":[18],"to":[19,24,28,84,100,112],"quickly":[20],"transfer":[21],"existing":[22,30,184],"skills":[23,31,44],"novel":[25,135],"tasks,":[26],"and":[27,60,88,90,116,166,197],"combine":[29],"with":[32,183,194],"newly":[33],"acquired":[34],"ones.":[35],"In":[36],"domains":[37],"where":[38,94],"tasks":[39],"are":[40],"solved":[41],"by":[42,149],"composing":[43,71],"this":[45,105,160],"capacity":[46],"holds":[47],"promise":[49],"of":[50,56,70,77,96,124,189,207],"dramatically":[51],"reducing":[52],"data":[54],"requirements":[55],"deep":[57],"RL":[58],"algorithms,":[59],"hence":[61],"increasing":[62],"their":[63,86],"applicability.":[64],"Recent":[65],"work":[66],"has":[67],"studied":[68],"ways":[69],"behaviors":[72],"represented":[73],"form":[76],"action-value":[78],"functions.":[79],"We":[80,158,179],"analyze":[81],"these":[82],"methods":[83],"highlight":[85],"strengths":[87],"weaknesses,":[89],"point":[91],"out":[92],"situations":[93],"each":[95],"them":[97],"susceptible":[99],"poor":[101],"performance.":[102],"To":[103],"perform":[104],"analysis":[106],"we":[107,132],"extend":[108],"generalized":[109],"policy":[110,143],"improvement":[111],"max-entropy":[114],"framework":[115],"introduce":[117],"a":[118,134,168,187],"method":[119,147],"for":[120],"practical":[122],"implementation":[123],"successor":[125],"features":[126],"continuous":[128,176,191],"action":[129,177],"spaces.":[130,178],"Then":[131],"propose":[133,167],"approach":[136,161,182],"which,":[137],"principle,":[139],"recovers":[140],"optimal":[142],"during":[144],"transfer.":[145],"This":[146],"works":[148],"explicitly":[150],"(discounted,":[153],"future)":[154],"divergence":[155],"between":[156],"policies.":[157],"study":[159],"tabular":[164],"case":[165],"scalable":[169],"variant":[170],"that":[171],"applicable":[173],"multi-dimensional":[175],"compare":[180],"our":[181],"ones":[185],"on":[186],"range":[188],"non-trivial":[190],"control":[192],"problems":[193],"compositional":[195],"structure,":[196],"demonstrate":[198],"qualitatively":[199],"better":[200],"performance":[201],"despite":[202],"not":[203],"requiring":[204],"simultaneous":[205],"observation":[206],"all":[208],"task":[209],"rewards.":[210]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2018-12-11T00:00:00"}