{"id":"https://openalex.org/W4389446019","doi":"https://doi.org/10.1007/s12559-023-10226-4","title":"A Novel Heuristic Exploration Method Based on Action Effectiveness Constraints to Relieve Loop Enhancement Effect in Reinforcement Learning with Sparse Rewards","display_name":"A Novel Heuristic Exploration Method Based on Action Effectiveness Constraints to Relieve Loop Enhancement Effect in Reinforcement Learning with Sparse Rewards","publication_year":2023,"publication_date":"2023-12-07","ids":{"openalex":"https://openalex.org/W4389446019","doi":"https://doi.org/10.1007/s12559-023-10226-4"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-023-10226-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s12559-023-10226-4","pdf_url":null,"source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075668463","display_name":"Zhenghongyuan Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenghongyuan Ni","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015900358","display_name":"Ye Jin","orcid":"https://orcid.org/0000-0002-8491-1391"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Jin","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-8491-1391","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China","Song Jiang Laboratory, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Song Jiang Laboratory, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066877556","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0002-0622-9258"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, 92 Xidazhi Street, Harbin, 150001, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075668463"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":null,"fwci":0.1704,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58810391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"16","issue":"2","first_page":"682","last_page":"700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9807000160217285,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.704848051071167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6825641989707947},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6299490928649902},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6047949194908142},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4926217198371887},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48402637243270874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47920283675193787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47389355301856995},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4424583911895752},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09360307455062866}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.704848051071167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825641989707947},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6299490928649902},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6047949194908142},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4926217198371887},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48402637243270874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47920283675193787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47389355301856995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4424583911895752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09360307455062866},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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:10.1007/s12559-023-10226-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s12559-023-10226-4","pdf_url":null,"source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6812708429","display_name":null,"funder_award_id":"51935005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1520048352","https://openalex.org/W1554318634","https://openalex.org/W1988526405","https://openalex.org/W2013830186","https://openalex.org/W2061868368","https://openalex.org/W2083537735","https://openalex.org/W2156211713","https://openalex.org/W2170899200","https://openalex.org/W2209913494","https://openalex.org/W2415726935","https://openalex.org/W2419612459","https://openalex.org/W2593237273","https://openalex.org/W2604960773","https://openalex.org/W2638556271","https://openalex.org/W2735952897","https://openalex.org/W2753971009","https://openalex.org/W2926842408","https://openalex.org/W2931767035","https://openalex.org/W2963523627","https://openalex.org/W2978336958","https://openalex.org/W2979879055","https://openalex.org/W3023592344","https://openalex.org/W3043559353","https://openalex.org/W3093528669","https://openalex.org/W3133533407","https://openalex.org/W3147079603","https://openalex.org/W3162434402","https://openalex.org/W3176644733","https://openalex.org/W3189576409","https://openalex.org/W3191504080","https://openalex.org/W3199364882","https://openalex.org/W3207342878","https://openalex.org/W3208112633","https://openalex.org/W3211609248","https://openalex.org/W3213022953","https://openalex.org/W3213746858","https://openalex.org/W4205475721","https://openalex.org/W4210453587","https://openalex.org/W4225935901","https://openalex.org/W4226068200","https://openalex.org/W4317553716","https://openalex.org/W4317815268","https://openalex.org/W4360584316","https://openalex.org/W4362665733","https://openalex.org/W4385268081","https://openalex.org/W6677916085"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4312407344","https://openalex.org/W2912415823"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}