{"id":"https://openalex.org/W3034988830","doi":"https://doi.org/10.24963/ijcai.2020/433","title":"I\u00b2HRL: Interactive Influence-based Hierarchical Reinforcement Learning","display_name":"I\u00b2HRL: Interactive Influence-based Hierarchical Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034988830","doi":"https://doi.org/10.24963/ijcai.2020/433","mag":"3034988830"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/433","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/433","pdf_url":"https://www.ijcai.org/proceedings/2020/0433.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0433.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023750802","display_name":"Rundong Wang","orcid":"https://orcid.org/0000-0001-6237-9472"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Rundong Wang","raw_affiliation_strings":["Nanyang Technological University","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552914","display_name":"Runsheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Runsheng Yu","raw_affiliation_strings":["Nanyang Technological University","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["Nanyang Technological University","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066651599","display_name":"Zinovi Rabinovich","orcid":"https://orcid.org/0000-0002-1796-8013"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zinovi Rabinovich","raw_affiliation_strings":["Nanyang Technological University","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023750802"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78038423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3131","last_page":"3138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9599999785423279,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9574999809265137,"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":0.9192522764205933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509713768959045},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7339376211166382},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5771746635437012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4788541793823242},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4665740728378296},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4505414068698883},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41358447074890137},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11209717392921448}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9192522764205933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509713768959045},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7339376211166382},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5771746635437012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4788541793823242},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4665740728378296},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4505414068698883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41358447074890137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11209717392921448},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/433","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/433","pdf_url":"https://www.ijcai.org/proceedings/2020/0433.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/433","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/433","pdf_url":"https://www.ijcai.org/proceedings/2020/0433.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034988830.pdf","grobid_xml":"https://content.openalex.org/works/W3034988830.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1678414046","https://openalex.org/W2096516049","https://openalex.org/W2187089797","https://openalex.org/W2210387432","https://openalex.org/W2257979135","https://openalex.org/W2342662072","https://openalex.org/W2606433045","https://openalex.org/W2787938642","https://openalex.org/W2945774545","https://openalex.org/W2949267040","https://openalex.org/W2949464762","https://openalex.org/W2950614095","https://openalex.org/W2963262099","https://openalex.org/W2963276097","https://openalex.org/W2963438456","https://openalex.org/W2963864421","https://openalex.org/W2964227312","https://openalex.org/W2976657239","https://openalex.org/W2990604886","https://openalex.org/W4293469690","https://openalex.org/W4294578467","https://openalex.org/W4295352814","https://openalex.org/W4298857966","https://openalex.org/W4394651706"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Hierarchical":[0,77],"reinforcement":[1],"learning":[2,184,188],"(HRL)":[3],"is":[4,19,43,158],"a":[5,23,29,71],"promising":[6],"approach":[7,179],"to":[8,28,50,62,96,147],"solve":[9],"tasks":[10,171],"with":[11,133,190],"long":[12],"time":[13],"horizons":[14],"and":[15,93,186],"sparse":[16],"rewards.":[17],"It":[18],"often":[20],"implemented":[21],"as":[22,114,116],"high-level":[24,36,94,99,103,127],"policy":[25,42,100,104,112,128],"assigning":[26],"subgoals":[27],"low-level":[30,41,92,111,139],"policy.":[31,140],"However,":[32],"it":[33],"suffers":[34],"the":[35,40,51,88,91,98,109,117,120,126,137,144,151,163,166,183],"non-stationarity":[37,47],"problem":[38],"since":[39],"constantly":[44],"changing.":[45],"The":[46,102],"also":[48],"leads":[49],"data":[52,58,157],"efficiency":[53],"problem:":[54],"policies":[55,95],"need":[56],"more":[57,148,155],"at":[59],"non-stationary":[60,152],"states":[61,153],"stabilize":[63,97,125],"training.":[64,101],"To":[65],"address":[66],"these":[67],"issues,":[68],"we":[69,86,123,142],"propose":[70,143],"novel":[72],"HRL":[73,192],"method:":[74],"Interactive":[75],"Influence-based":[76],"Reinforcement":[78],"Learning":[79],"(I^2HRL).":[80],"First,":[81],"inspired":[82],"by":[83,175],"agent":[84],"modeling,":[85],"enable":[87],"interaction":[89],"between":[90],"makes":[105],"decisions":[106],"conditioned":[107],"on":[108,136],"received":[110],"representation":[113],"well":[115],"state":[118],"of":[119,165],"environment.":[121],"Second,":[122],"furthermore":[124],"via":[129],"an":[130],"information-theoretic":[131],"regularization":[132],"minimal":[134],"dependence":[135],"changing":[138],"Third,":[141],"influence-based":[145],"exploration":[146],"frequently":[149],"visit":[150],"where":[154],"transition":[156],"needed.":[159],"We":[160],"experimentally":[161],"validate":[162],"effectiveness":[164],"proposed":[167],"solution":[168],"in":[169,172],"several":[170],"MuJoCo":[173],"domains":[174],"demonstrating":[176],"that":[177],"our":[178],"can":[180],"significantly":[181],"boost":[182],"performance":[185],"accelerate":[187],"compared":[189],"state-of-the-art":[191],"methods.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}