{"id":"https://openalex.org/W4385764347","doi":"https://doi.org/10.24963/ijcai.2023/506","title":"Hierarchical State Abstraction based on Structural Information Principles","display_name":"Hierarchical State Abstraction based on Structural Information Principles","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764347","doi":"https://doi.org/10.24963/ijcai.2023/506"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/506","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/506","pdf_url":"https://www.ijcai.org/proceedings/2023/0506.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second 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/2023/0506.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034025309","display_name":"Xianghua Zeng","orcid":"https://orcid.org/0000-0003-4775-6764"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xianghua Zeng","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740618","display_name":"Hao Peng","orcid":"https://orcid.org/0000-0001-7422-630X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Peng","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041305250","display_name":"Angsheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Angsheng Li","raw_affiliation_strings":["Beihang University","Zhongguancun Laboratory","Beihang University; Zhongguancun Laboratory"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]},{"raw_affiliation_string":"Beihang University; Zhongguancun Laboratory","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474600","display_name":"Chunyang Liu","orcid":"https://orcid.org/0000-0002-3694-0075"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyang Liu","raw_affiliation_strings":["Didi Chuxing"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071709543","display_name":"Lifang He","orcid":"https://orcid.org/0000-0001-7810-9071"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifang He","raw_affiliation_strings":["Lehigh University"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034025309"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.9381,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92750761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4549","last_page":"4557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9883999824523926,"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/abstraction","display_name":"Abstraction","score":0.7883518934249878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832024097442627},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5836617946624756},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5723257660865784},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5083815455436707},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4483717978000641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4363189935684204},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4286876320838928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4232247471809387},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4206992983818054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39470258355140686},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35794901847839355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10201114416122437}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7883518934249878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832024097442627},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5836617946624756},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5723257660865784},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5083815455436707},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4483717978000641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4363189935684204},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4286876320838928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4232247471809387},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4206992983818054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39470258355140686},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35794901847839355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10201114416122437},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/506","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/506","pdf_url":"https://www.ijcai.org/proceedings/2023/0506.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/506","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/506","pdf_url":"https://www.ijcai.org/proceedings/2023/0506.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second 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":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1100817172","display_name":null,"funder_award_id":"619320","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1312784247","display_name":null,"funder_award_id":"MRI-2215789","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2142201510","display_name":"III: Small: Exploiting the Massive User Generated Utterances for Intent Mining under Scarce Annotations","funder_award_id":"1909323","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3118254216","display_name":"III: Medium: Collaborative Research: An Extensible Heterogeneous Network Embedding Framework with Application Specific Adaptation","funder_award_id":"1763325","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3826598724","display_name":null,"funder_award_id":"III-1763325, III-1909323, III-2106758, SaTC-1930941","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4320322031","display_name":"III: Medium: Collaborative Research: Self-Supervised Recommender System Learning with Application Specific Adaption","funder_award_id":"2106758","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G519982818","display_name":"The Thermo-Chemical State and Thermo-Tectonic Evolution of Cratons and Deep Cratonic Lithosphere","funder_award_id":"0001029","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5722720762","display_name":null,"funder_award_id":"III-2106758","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6566754452","display_name":null,"funder_award_id":"001250","funder_id":"https://openalex.org/F4320310365","funder_display_name":"Lehigh University"},{"id":"https://openalex.org/G6593982251","display_name":null,"funder_award_id":"2215789","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7211111366","display_name":null,"funder_award_id":"S00010293","funder_id":"https://openalex.org/F4320310365","funder_display_name":"Lehigh University"},{"id":"https://openalex.org/G7537086629","display_name":null,"funder_award_id":"6193200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7633400475","display_name":null,"funder_award_id":"III-1763325","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7817793019","display_name":null,"funder_award_id":"III-1909323","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G883900857","display_name":null,"funder_award_id":"SaTC-1930941","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8939654172","display_name":null,"funder_award_id":"61932002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G979281235","display_name":"SaTC: CORE: Small: Collaborative: Learning Dynamic and Robust Defenses Against Co-Adaptive Spammers","funder_award_id":"1930941","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310365","display_name":"Lehigh University","ror":"https://ror.org/012afjb06"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764347.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2029058516","https://openalex.org/W2076337359","https://openalex.org/W2118022839","https://openalex.org/W2145339207","https://openalex.org/W2157331557","https://openalex.org/W2397240726","https://openalex.org/W2460678386","https://openalex.org/W2468354762","https://openalex.org/W2482498454","https://openalex.org/W2781726626","https://openalex.org/W2803178532","https://openalex.org/W2885386724","https://openalex.org/W2920362155","https://openalex.org/W2948345531","https://openalex.org/W2970786075","https://openalex.org/W2973525135","https://openalex.org/W3021708257","https://openalex.org/W3036619998","https://openalex.org/W3115293622","https://openalex.org/W3125947392","https://openalex.org/W3175558129","https://openalex.org/W3217103056","https://openalex.org/W4210746245","https://openalex.org/W4283729103","https://openalex.org/W4283796568","https://openalex.org/W4283802063","https://openalex.org/W4285604301","https://openalex.org/W4287123420","https://openalex.org/W4288294128","https://openalex.org/W4288335419","https://openalex.org/W4306316942","https://openalex.org/W4313495421","https://openalex.org/W4321480062","https://openalex.org/W4328113578","https://openalex.org/W4382202881","https://openalex.org/W4382318991"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2045155990","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4313163053","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W1985727224"],"abstract_inverted_index":{"State":[0,45],"abstraction":[1,95,125],"optimizes":[2],"decision-making":[3],"by":[4],"ignoring":[5],"irrelevant":[6],"environmental":[7],"information":[8,26,101],"in":[9,24,103],"reinforcement":[10],"learning":[11],"with":[12,121,157],"rich":[13],"observations.":[14],"Nevertheless,":[15],"recent":[16],"approaches":[17],"focus":[18],"on":[19,31,108],"adequate":[20],"representational":[21],"capacities":[22],"resulting":[23],"essential":[25,100],"loss,":[27],"affecting":[28],"their":[29,163],"performances":[30,164],"challenging":[32],"tasks.":[33],"In":[34],"this":[35],"article,":[36],"we":[37,143],"propose":[38],"a":[39,81,109,149],"novel":[40],"mathematical":[41],"Structural":[42],"Information":[43],"principles-based":[44],"Abstraction":[46],"framework,":[47],"namely":[48],"SISA,":[49],"from":[50],"the":[51],"information-theoretic":[52],"perspective.":[53],"Specifically,":[54],"an":[55,70],"unsupervised,":[56],"adaptive":[57],"hierarchical":[58,93],"state":[59,94,104,124],"clustering":[60],"method":[61],"without":[62],"requiring":[63],"manual":[64],"assistance":[65],"is":[66,74,148],"presented,":[67],"and":[68,85,96,113,133,139],"meanwhile,":[69],"optimal":[71],"encoding":[72],"tree":[73,79],"generated.":[75],"On":[76],"each":[77],"non-root":[78],"node,":[80],"new":[82],"aggregation":[83],"function":[84],"condition":[86],"structural":[87],"entropy":[88],"are":[89],"designed":[90],"to":[91,137,161],"achieve":[92],"compensate":[97],"for":[98],"sampling-induced":[99],"loss":[102],"abstraction.":[105],"Empirical":[106],"evaluations":[107],"visual":[110],"gridworld":[111],"domain":[112],"six":[114],"continuous":[115],"control":[116],"benchmarks":[117],"demonstrate":[118],"that,":[119],"compared":[120],"five":[122],"SOTA":[123],"approaches,":[126],"SISA":[127,147],"significantly":[128],"improves":[129],"mean":[130],"episode":[131],"reward":[132],"sample":[134],"efficiency":[135],"up":[136],"18.98":[138],"44.44%,":[140],"respectively.":[141],"Besides,":[142],"experimentally":[144],"show":[145],"that":[146,152],"general":[150],"framework":[151],"can":[153],"be":[154],"flexibly":[155],"integrated":[156],"different":[158],"representation-learning":[159],"objectives":[160],"improve":[162],"further.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}