{"id":"https://openalex.org/W4416400728","doi":"https://doi.org/10.1016/j.neunet.2025.108299","title":"Hit the spot: Reachability guided subgoal generation for hierarchical reinforcement learning in stochastic environments","display_name":"Hit the spot: Reachability guided subgoal generation for hierarchical reinforcement learning in stochastic environments","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416400728","doi":"https://doi.org/10.1016/j.neunet.2025.108299","pmid":"https://pubmed.ncbi.nlm.nih.gov/41289642"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2025.108299","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neunet.2025.108299","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bo Chen","orcid":"https://orcid.org/0000-0001-6002-5611"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications china, China"],"raw_orcid":"https://orcid.org/0000-0001-6002-5611","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications china, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020164684","display_name":"Quan Yuan","orcid":"https://orcid.org/0000-0002-2552-333X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Yuan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications china, China. Electronic address: yuanquan@bupt.edu.cn"],"raw_orcid":"https://orcid.org/0000-0002-2552-333X","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications china, China. Electronic address: yuanquan@bupt.edu.cn","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047834526","display_name":"Guiyang Luo","orcid":"https://orcid.org/0000-0002-1912-8536"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiyang Luo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications china, China"],"raw_orcid":"https://orcid.org/0000-0002-1912-8536","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications china, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084526966","display_name":"Yilin Liu","orcid":"https://orcid.org/0000-0003-4106-6674"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications china, China"],"raw_orcid":"https://orcid.org/0000-0003-4106-6674","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications china, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Pan","orcid":"https://orcid.org/0000-0003-4313-3324"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Pan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications china, China"],"raw_orcid":"https://orcid.org/0000-0003-4313-3324","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications china, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697367","display_name":"Jinglin Li","orcid":"https://orcid.org/0000-0002-6720-9533"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglin Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications china, China"],"raw_orcid":"https://orcid.org/0000-0002-6720-9533","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications china, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020164684"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17948433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"196","issue":null,"first_page":"108299","last_page":"108299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9610000252723694,"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":0.9610000252723694,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reachability","display_name":"Reachability","score":0.8906999826431274},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7250999808311462},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5615000128746033},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3953000009059906},{"id":"https://openalex.org/keywords/stochastic-modelling","display_name":"Stochastic modelling","score":0.3953000009059906},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.3686999976634979}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.8906999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7250999808311462},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5615000128746033},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2533999979496002}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.neunet.2025.108299","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neunet.2025.108299","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:41289642","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41289642","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural networks : the official journal of the International Neural Network Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1612511543","display_name":null,"funder_award_id":"20230484364","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G1773702449","display_name":null,"funder_award_id":"2022QNRC001","funder_id":"https://openalex.org/F4320311778","funder_display_name":"China Association for Science and Technology"},{"id":"https://openalex.org/G6999783098","display_name":null,"funder_award_id":"62272053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8269616727","display_name":null,"funder_award_id":"62472048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8459559404","display_name":null,"funder_award_id":"62,272,053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1592847719","https://openalex.org/W2048411524","https://openalex.org/W2109910161","https://openalex.org/W3162722130","https://openalex.org/W3168892396","https://openalex.org/W4207021923","https://openalex.org/W4313478129","https://openalex.org/W4377695283"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-11-20T00:00:00"}