{"id":"https://openalex.org/W2963709735","doi":"https://doi.org/10.24963/ijcai.2018/675","title":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","display_name":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2963709735","doi":"https://doi.org/10.24963/ijcai.2018/675","mag":"2963709735"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/675","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/675","pdf_url":"https://www.ijcai.org/proceedings/2018/0675.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0675.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101564849","display_name":"Fangkai Yang","orcid":"https://orcid.org/0000-0002-3089-0345"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]},{"id":"https://openalex.org/I4210089311","display_name":"Yanan University Affiliated Hospital","ror":"https://ror.org/006992e45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089311"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Fangkai Yang","raw_affiliation_strings":["Maana Inc","Maana Inc., Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maana Inc","institution_ids":["https://openalex.org/I4210089311"]},{"raw_affiliation_string":"Maana Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025744129","display_name":"Daoming Lyu","orcid":"https://orcid.org/0000-0003-2625-9865"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daoming Lyu","raw_affiliation_strings":["Auburn University","Auburn University, Auburn, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727812","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-5426-515X"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Auburn University","Auburn University, Auburn, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109278826","display_name":"Steven Gustafson","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]},{"id":"https://openalex.org/I4210089311","display_name":"Yanan University Affiliated Hospital","ror":"https://ror.org/006992e45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089311"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Steven Gustafson","raw_affiliation_strings":["Maana Inc","Maana Inc., Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maana Inc","institution_ids":["https://openalex.org/I4210089311"]},{"raw_affiliation_string":"Maana Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4860","last_page":"4866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9940999746322632,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9824000000953674,"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":0.8976914882659912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7704144716262817},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6675890684127808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.602952778339386},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5737863779067993},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49877238273620605},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.45021727681159973},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43728768825531006},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.4249425530433655},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10479941964149475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0624350905418396}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8976914882659912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704144716262817},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6675890684127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.602952778339386},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5737863779067993},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49877238273620605},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.45021727681159973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43728768825531006},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.4249425530433655},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10479941964149475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0624350905418396},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/675","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/675","pdf_url":"https://www.ijcai.org/proceedings/2018/0675.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/675","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/675","pdf_url":"https://www.ijcai.org/proceedings/2018/0675.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309904","display_name":"Auburn University","ror":"https://ror.org/02v80fc35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963709735.pdf","grobid_xml":"https://content.openalex.org/works/W2963709735.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1549353711","https://openalex.org/W1605439581","https://openalex.org/W1814441753","https://openalex.org/W1855398616","https://openalex.org/W1903938722","https://openalex.org/W1959035372","https://openalex.org/W2049791401","https://openalex.org/W2109910161","https://openalex.org/W2138162238","https://openalex.org/W2145339207","https://openalex.org/W2149280200","https://openalex.org/W2158548602","https://openalex.org/W2158779828","https://openalex.org/W2160808139","https://openalex.org/W2170655684","https://openalex.org/W2518731509","https://openalex.org/W2521453195","https://openalex.org/W2578289159","https://openalex.org/W2586777479","https://openalex.org/W2950040888","https://openalex.org/W2963262099","https://openalex.org/W3101355526","https://openalex.org/W4214717370","https://openalex.org/W4229915002","https://openalex.org/W4301210146"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Reinforcement":[0,14],"learning":[1,15,18,67],"and":[2,49,88,90,110],"symbolic":[3,39,62,98,112],"planning":[4,34,63],"have":[5],"both":[6],"been":[7],"used":[8,81],"to":[9,46,69,82,97,100,106],"build":[10],"intelligent":[11],"autonomous":[12],"agents.":[13],"relies":[16,35],"on":[17,36,121],"from":[19],"interactions":[20],"with":[21,64,71,76],"real":[22],"world,":[23],"which":[24,41],"often":[25],"requires":[26],"an":[27],"unfeasibly":[28],"large":[29],"amount":[30],"of":[31,124],"experience.":[32],"Symbolic":[33,78],"manually":[37],"crafted":[38],"knowledge,":[40],"may":[42],"not":[43],"be":[44],"robust":[45,111],"domain":[47],"uncertainties":[48],"changes.":[50],"In":[51],"this":[52],"paper":[53],"we":[54],"present":[55],"a":[56],"unified":[57],"framework":[58,118],"PEORL":[59],"that":[60],"integrates":[61],"hierarchical":[65],"reinforcement":[66],"(HRL)":[68],"cope":[70],"decision-making":[72],"in":[73,114],"dynamic":[74],"environment":[75],"uncertainties.":[77],"plans":[79,113],"are":[80],"guide":[83],"the":[84,91],"agent's":[85],"task":[86],"execution":[87],"learning,":[89],"learned":[92],"experience":[93],"is":[94,119],"fed":[95],"back":[96],"knowledge":[99],"improve":[101],"planning.":[102],"This":[103],"method":[104],"leads":[105],"rapid":[107],"policy":[108],"search":[109],"complex":[115],"domains.":[116],"The":[117],"tested":[120],"benchmark":[122],"domains":[123],"HRL.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}