{"id":"https://openalex.org/W4402660054","doi":"https://doi.org/10.1109/cis-ram61939.2024.10672981","title":"Learning Efficient Representations for Goal-conditioned Reinforcement Learning via Tabu Search","display_name":"Learning Efficient Representations for Goal-conditioned Reinforcement Learning via Tabu Search","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4402660054","doi":"https://doi.org/10.1109/cis-ram61939.2024.10672981"},"language":"en","primary_location":{"id":"doi:10.1109/cis-ram61939.2024.10672981","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cis-ram61939.2024.10672981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102586353","display_name":"Tianhao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Liang","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808017","display_name":"Tianyang Chen","orcid":"https://orcid.org/0000-0002-6714-3159"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052583539","display_name":"Xianwei Chen","orcid":"https://orcid.org/0000-0002-5646-3245"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianwei Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041199618","display_name":"Qinyuan Ren","orcid":"https://orcid.org/0000-0001-9487-2675"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyuan Ren","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"328","last_page":"333"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8389028906822205},{"id":"https://openalex.org/keywords/tabu-search","display_name":"Tabu search","score":0.7193892002105713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6670409440994263},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5345913767814636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4682301878929138},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33905738592147827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3292381763458252},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18317830562591553},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09365248680114746}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8389028906822205},{"id":"https://openalex.org/C123370116","wikidata":"https://www.wikidata.org/wiki/Q1424540","display_name":"Tabu search","level":2,"score":0.7193892002105713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670409440994263},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5345913767814636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4682301878929138},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33905738592147827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292381763458252},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18317830562591553},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09365248680114746}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cis-ram61939.2024.10672981","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cis-ram61939.2024.10672981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2823112946","https://openalex.org/W2914358862","https://openalex.org/W2963689319","https://openalex.org/W2967895468","https://openalex.org/W3037784242","https://openalex.org/W3092037789","https://openalex.org/W3096609285","https://openalex.org/W3113139432","https://openalex.org/W4282019706","https://openalex.org/W4285601030","https://openalex.org/W4298857966","https://openalex.org/W4307078757","https://openalex.org/W4383108731","https://openalex.org/W6616173779","https://openalex.org/W6637967152","https://openalex.org/W6753060773","https://openalex.org/W6756257017","https://openalex.org/W6783692663","https://openalex.org/W6838841256","https://openalex.org/W6845737239","https://openalex.org/W6849915793","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2224940485","https://openalex.org/W2168643831","https://openalex.org/W2075514833","https://openalex.org/W2381791171","https://openalex.org/W4247343174","https://openalex.org/W1987877777","https://openalex.org/W2366189044","https://openalex.org/W2365741636","https://openalex.org/W2011733276","https://openalex.org/W4231225946"],"abstract_inverted_index":{"An":[0],"intelligent":[1],"robot":[2,25],"should":[3],"understand":[4],"the":[5,20,35,43,50,95,98,110,122],"user-specified":[6],"goals":[7,48],"and":[8,42,93,119],"execute":[9],"corresponding":[10],"skills":[11],"to":[12,29,60,126],"fulfill":[13],"them.":[14],"In":[15,27],"this":[16],"paper,":[17],"we":[18,70],"study":[19],"problem":[21],"of":[22,38,52,97],"visual":[23,39],"goal-conditioned":[24,40,117],"manipulation.":[26],"contrast":[28],"previous":[30],"methods,":[31],"our":[32],"method":[33],"improves":[34],"successful":[36],"rate":[37],"tasks":[41],"generation":[44],"ability":[45],"toward":[46],"different":[47],"from":[49],"aspect":[51],"network":[53,74,80,100,113],"structure.":[54],"We":[55,91],"also":[56],"use":[57],"Tabu":[58],"Search":[59],"select":[61],"higher-parameters":[62],"for":[63],"best":[64],"learning":[65],"results.":[66],"To":[67],"that":[68,109],"end,":[69],"propose":[71],"a":[72],"slot-based":[73,112],"within":[75],"Goal-Conditioned":[76],"Reinforcement-Learning":[77],"framework.":[78],"The":[79,106],"can":[81,114],"focus":[82],"on":[83],"task-related":[84],"areas":[85],"while":[86],"filtering":[87],"out":[88],"environmental":[89],"disturbance.":[90],"trained":[92],"validated":[94],"effectiveness":[96],"proposed":[99,111],"in":[101],"two":[102],"simulation":[103],"environment":[104],"tasks.":[105],"experiments":[107],"proved":[108],"efficiently":[115],"extract":[116],"information":[118],"successfully":[120],"complete":[121],"given":[123],"task":[124],"compared":[125],"baselines.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}