{"id":"https://openalex.org/W3041985709","doi":null,"title":"Exploration via Cost-Aware Subgoal Design","display_name":"Exploration via Cost-Aware Subgoal Design","publication_year":2019,"publication_date":"2019-10-21","ids":{"openalex":"https://openalex.org/W3041985709","mag":"3041985709"},"language":"en","primary_location":{"id":"mag:3041985709","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.09143","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/1910.09143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022993156","display_name":"Yijia Wang","orcid":"https://orcid.org/0000-0002-3549-2581","observed_orcids":["https://orcid.org/0000-0002-3549-2581"]},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijia Wang","raw_affiliation_strings":["Univ. of Pittsburgh"],"raw_orcid":"https://orcid.org/0000-0002-3549-2581","affiliations":[{"raw_affiliation_string":"Univ. of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069492649","display_name":"Matthias Poloczek","orcid":"https://orcid.org/0000-0003-4178-5521","observed_orcids":["https://orcid.org/0000-0003-4178-5521"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Poloczek","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4178-5521","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074472243","display_name":"Daniel Jiang","orcid":"https://orcid.org/0000-0002-5388-8061","observed_orcids":["https://orcid.org/0000-0002-5388-8061"]},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel R. Jiang","raw_affiliation_strings":["Univ. of Pittsburgh"],"raw_orcid":"https://orcid.org/0000-0002-5388-8061","affiliations":[{"raw_affiliation_string":"Univ. of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0008999999845400453,"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/exploration","display_name":"exploration","score":0.609000027179718},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.8159999847412109},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.5680000185966492},{"id":"https://openalex.org/keywords/delayed-rewards","display_name":"delayed rewards","score":0.8569999933242798},{"id":"https://openalex.org/keywords/unknown-environments","display_name":"unknown environments","score":0.6309999823570251},{"id":"https://openalex.org/keywords/asymptotic-optimality","display_name":"asymptotic optimality","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7165470123291016},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7117833495140076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991563439369202},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5968024134635925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5032493472099304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977426826953888},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.47574281692504883},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4461207091808319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3497728109359741},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.26498234272003174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13452208042144775},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09516078233718872},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3041985709","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.09143","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:3041985709","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.09143","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":79,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1499408472","https://openalex.org/W1510052597","https://openalex.org/W1529817821","https://openalex.org/W1536323281","https://openalex.org/W1542595278","https://openalex.org/W1569788011","https://openalex.org/W1583116672","https://openalex.org/W1586944634","https://openalex.org/W1746819321","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1825573441","https://openalex.org/W1969074599","https://openalex.org/W1974043469","https://openalex.org/W1981158530","https://openalex.org/W2004808074","https://openalex.org/W2031727428","https://openalex.org/W2046376809","https://openalex.org/W2066713014","https://openalex.org/W2072302356","https://openalex.org/W2079247031","https://openalex.org/W2099201756","https://openalex.org/W2106008664","https://openalex.org/W2107112577","https://openalex.org/W2111764152","https://openalex.org/W2112874374","https://openalex.org/W2113145584","https://openalex.org/W2121863487","https://openalex.org/W2131241448","https://openalex.org/W2131627640","https://openalex.org/W2149721706","https://openalex.org/W2151210636","https://openalex.org/W2154231454","https://openalex.org/W2155927283","https://openalex.org/W2163602945","https://openalex.org/W2168966637","https://openalex.org/W2169743339","https://openalex.org/W2200000192","https://openalex.org/W2266822037","https://openalex.org/W2280163991","https://openalex.org/W2342840547","https://openalex.org/W2416477367","https://openalex.org/W2441569124","https://openalex.org/W2470693974","https://openalex.org/W2489939061","https://openalex.org/W2534269850","https://openalex.org/W2561776174","https://openalex.org/W2578206533","https://openalex.org/W2593766708","https://openalex.org/W2595845486","https://openalex.org/W2596982695","https://openalex.org/W2604763608","https://openalex.org/W2609169452","https://openalex.org/W2724169821","https://openalex.org/W2751973545","https://openalex.org/W2755546070","https://openalex.org/W2765602917","https://openalex.org/W2766447205","https://openalex.org/W2772089072","https://openalex.org/W2783201493","https://openalex.org/W2796835114","https://openalex.org/W2890019192","https://openalex.org/W2898963091","https://openalex.org/W2945322269","https://openalex.org/W2945677399","https://openalex.org/W2962747693","https://openalex.org/W2963176272","https://openalex.org/W2963276097","https://openalex.org/W2963412383","https://openalex.org/W2963439757","https://openalex.org/W2963742654","https://openalex.org/W2963815651","https://openalex.org/W2969999645","https://openalex.org/W2970717270","https://openalex.org/W2970782456","https://openalex.org/W2974778612","https://openalex.org/W3001779429","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W4308245670","https://openalex.org/W7019241752","https://openalex.org/W7118022272","https://openalex.org/W7127340082","https://openalex.org/W2509828103","https://openalex.org/W3192782817","https://openalex.org/W1547361108","https://openalex.org/W3186440918","https://openalex.org/W2945263287","https://openalex.org/W7096848018"],"abstract_inverted_index":{"The":[0,26],"problem":[1],"of":[2,28,39,65,71,121,133,144],"exploration":[3,63],"in":[4,45,60,88],"unknown":[5,86],"environments":[6],"continues":[7],"to":[8,42,96,127],"pose":[9],"a":[10,109,142],"challenge":[11],"for":[12,36,113],"reinforcement":[13],"learning":[14],"algorithms,":[15],"as":[16],"interactions":[17,103],"with":[18,31,47,118],"the":[19,37,62,66,72,89,102,119,124,130],"environment":[20,46],"are":[21,104],"usually":[22],"expensive":[23],"or":[24],"limited.":[25],"technique":[27],"setting":[29],"subgoals":[30],"an":[32,57,82,85,134,149],"intrinsic":[33],"reward":[34],"allows":[35],"use":[38],"supplemental":[40],"feedback":[41],"aid":[43],"agent":[44,67,83],"sparse":[48],"and":[49,91,123,146],"delayed":[50],"rewards.":[51],"In":[52,75],"fact,":[53],"it":[54],"can":[55],"be":[56],"effective":[58],"tool":[59],"directing":[61],"behavior":[64],"toward":[68],"useful":[69],"parts":[70],"state":[73],"space.":[74],"this":[76],"paper,":[77],"we":[78],"consider":[79],"problems":[80],"where":[81,101],"faces":[84],"task":[87],"future":[90],"is":[92],"given":[93],"prior":[94],"opportunities":[95],"``practice''":[97],"on":[98,141],"related":[99],"tasks":[100,145],"still":[105],"expensive.":[106],"We":[107,136],"propose":[108],"one-step":[110],"Bayes-optimal":[111],"algorithm":[112],"selecting":[114],"subgoal":[115],"designs,":[116],"along":[117],"number":[120],"episodes":[122],"episode":[125],"length,":[126],"efficiently":[128],"maximize":[129],"expected":[131],"performance":[132,140],"agent.":[135],"demonstrate":[137],"its":[138],"excellent":[139],"variety":[143],"also":[147],"prove":[148],"asymptotic":[150],"optimality":[151],"guarantee.":[152]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-16T00:00:00"}