{"id":"https://openalex.org/W4393161394","doi":"https://doi.org/10.1609/aaai.v38i21.30504","title":"Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract)","display_name":"Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract)","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393161394","doi":"https://doi.org/10.1609/aaai.v38i21.30504"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i21.30504","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v38i21.30504","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30504/32640","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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30504/32640","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000171089","display_name":"Brandon Rozek","orcid":"https://orcid.org/0000-0002-4537-559X"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brandon Rozek","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078925783","display_name":"Junkyu Lee","orcid":"https://orcid.org/0000-0003-1985-5116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junkyu Lee","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025268861","display_name":"Harsha Kokel","orcid":"https://orcid.org/0000-0002-7548-3719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harsha Kokel","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103010384","display_name":"Michael B. Katz","orcid":"https://orcid.org/0000-0003-1021-1402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Katz","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037217032","display_name":"Shirin Sohrabi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shirin Sohrabi","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000171089"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.3093,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47896951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"38","issue":"21","first_page":"23635","last_page":"23636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5126000046730042,"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":0.5126000046730042,"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":0.7265968918800354},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6751152276992798},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5183151960372925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5151680707931519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46646320819854736},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27654436230659485},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07005757093429565},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05726960301399231}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7265968918800354},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6751152276992798},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5183151960372925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5151680707931519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46646320819854736},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27654436230659485},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07005757093429565},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05726960301399231},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v38i21.30504","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v38i21.30504","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30504/32640","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,"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i21.30504","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v38i21.30504","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30504/32640","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,"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":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393161394.pdf"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4298178440"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1994680671","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2000283393","https://openalex.org/W2002320543","https://openalex.org/W2150232912","https://openalex.org/W2054940838","https://openalex.org/W1977959518"],"abstract_inverted_index":{"Partially":[0],"observable":[1],"Markov":[2],"decision":[3],"processes":[4],"(POMDPs)":[5],"challenge":[6],"reinforcement":[7,49],"learning":[8,50],"agents":[9],"due":[10],"to":[11,28,33,46,56,70,93],"incomplete":[12],"knowledge":[13],"of":[14,65,101],"the":[15,60,75,82,95,111],"environment.":[16],"Even":[17],"assuming":[18],"monotonicity":[19],"in":[20,77],"uncertainty,":[21],"it":[22],"is":[23,90],"difficult":[24],"for":[25,36,103],"an":[26,78],"agent":[27,61,83,121],"know":[29],"how":[30,45,69,116],"and":[31,52,68,114],"when":[32,59],"stop":[34],"exploring":[35],"a":[37,86,99],"given":[38],"task.":[39],"In":[40],"this":[41],"abstract,":[42],"we":[43],"discuss":[44],"use":[47],"hierarchical":[48],"(HRL)":[51],"AI":[53],"Planning":[54],"(AIP)":[55],"improve":[57,120],"exploration":[58,118],"knows":[62],"possible":[63],"valuations":[64],"unknown":[66],"predicates":[67],"discover":[71],"them.":[72],"By":[73],"encoding":[74],"uncertainty":[76],"abstract":[79],"planning":[80],"model,":[81],"can":[84],"derive":[85],"high-level":[87],"plan":[88],"which":[89],"then":[91],"used":[92],"decompose":[94],"overall":[96],"POMDP":[97],"into":[98],"tree":[100],"semi-POMDPs":[102],"training.":[104],"We":[105],"evaluate":[106],"our":[107],"agent's":[108],"performance":[109],"on":[110],"MiniGrid":[112],"domain":[113],"show":[115],"guided":[117],"may":[119],"performance.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}