{"id":"https://openalex.org/W3167965394","doi":"https://doi.org/10.24963/ijcai.2022/474","title":"PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations","display_name":"PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W3167965394","doi":"https://doi.org/10.24963/ijcai.2022/474","mag":"3167965394"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/474","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/474","pdf_url":"https://www.ijcai.org/proceedings/2022/0474.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0474.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086322992","display_name":"Tong Sang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Sang","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176048","display_name":"Hongyao Tang","orcid":"https://orcid.org/0000-0001-7478-7684"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyao Tang","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028605963","display_name":"Yi Ma","orcid":"https://orcid.org/0000-0001-9375-6605"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ma","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101312842","display_name":"Jianye Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058179613","display_name":"Yan Zheng","orcid":"https://orcid.org/0000-0002-5016-6549"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005604730","display_name":"Zhaopeng Meng","orcid":"https://orcid.org/0000-0001-6019-5952"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopeng Meng","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771193","display_name":"Boyan Li","orcid":"https://orcid.org/0009-0005-1359-7218"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyan Li","raw_affiliation_strings":["Tianjin University","College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Northwestern Polytechnical University","School of Artificial Intelligence, Optics and Electronics (iOPEN) and School of Cybersecurity, Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN) and School of Cybersecurity, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5086322992"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00100716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3416","last_page":"3422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9830999970436096,"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/T10603","display_name":"Smart Grid Energy Management","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.7928742170333862},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7879772186279297},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7683355808258057},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5787028074264526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5735951662063599},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5605834126472473},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5250161290168762},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49469301104545593},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45810768008232117},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4233609437942505},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3273143768310547},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07795313000679016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07540208101272583},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07353302836418152},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07084906101226807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928742170333862},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7879772186279297},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7683355808258057},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5787028074264526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5735951662063599},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5605834126472473},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5250161290168762},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49469301104545593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45810768008232117},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4233609437942505},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3273143768310547},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07795313000679016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07540208101272583},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07353302836418152},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07084906101226807},{"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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/474","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/474","pdf_url":"https://www.ijcai.org/proceedings/2022/0474.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/474","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/474","pdf_url":"https://www.ijcai.org/proceedings/2022/0474.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3794980888","display_name":null,"funder_award_id":"11931015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5677026016","display_name":null,"funder_award_id":"2020TD-013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G714647208","display_name":null,"funder_award_id":"62025602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8252796664","display_name":null,"funder_award_id":"U1803263","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8734799983","display_name":null,"funder_award_id":"62106172","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167965394.pdf","grobid_xml":"https://content.openalex.org/works/W3167965394.grobid-xml"},"referenced_works_count":98,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2013825190","https://openalex.org/W2025713906","https://openalex.org/W2066251678","https://openalex.org/W2111935653","https://openalex.org/W2116339921","https://openalex.org/W2120181489","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2257979135","https://openalex.org/W2412782625","https://openalex.org/W2495425901","https://openalex.org/W2499540656","https://openalex.org/W2507318699","https://openalex.org/W2557283755","https://openalex.org/W2565639579","https://openalex.org/W2574978968","https://openalex.org/W2580175322","https://openalex.org/W2596758708","https://openalex.org/W2604763608","https://openalex.org/W2606722458","https://openalex.org/W2736601468","https://openalex.org/W2770241596","https://openalex.org/W2803926500","https://openalex.org/W2805003733","https://openalex.org/W2898436992","https://openalex.org/W2902625698","https://openalex.org/W2904246096","https://openalex.org/W2907886210","https://openalex.org/W2948130861","https://openalex.org/W2949608212","https://openalex.org/W2949759968","https://openalex.org/W2952526277","https://openalex.org/W2952899695","https://openalex.org/W2953212265","https://openalex.org/W2954070046","https://openalex.org/W2956434358","https://openalex.org/W2962902376","https://openalex.org/W2963287528","https://openalex.org/W2963341956","https://openalex.org/W2963452728","https://openalex.org/W2963674932","https://openalex.org/W2963923407","https://openalex.org/W2964081807","https://openalex.org/W2964125494","https://openalex.org/W2964299589","https://openalex.org/W2965862774","https://openalex.org/W2978696242","https://openalex.org/W2982316857","https://openalex.org/W2990747716","https://openalex.org/W2999204576","https://openalex.org/W3000499753","https://openalex.org/W3009007264","https://openalex.org/W3010035731","https://openalex.org/W3015921997","https://openalex.org/W3021034371","https://openalex.org/W3034752558","https://openalex.org/W3034956653","https://openalex.org/W3035080282","https://openalex.org/W3035180000","https://openalex.org/W3035524453","https://openalex.org/W3036928441","https://openalex.org/W3038428716","https://openalex.org/W3042228527","https://openalex.org/W3092446983","https://openalex.org/W3098372854","https://openalex.org/W3101442004","https://openalex.org/W3101584733","https://openalex.org/W3107308507","https://openalex.org/W3107554570","https://openalex.org/W3115293622","https://openalex.org/W3121197820","https://openalex.org/W3121852482","https://openalex.org/W3124971693","https://openalex.org/W3129093240","https://openalex.org/W3130112836","https://openalex.org/W3130287600","https://openalex.org/W3130658283","https://openalex.org/W3143219376","https://openalex.org/W3144743376","https://openalex.org/W3158533115","https://openalex.org/W3163745263","https://openalex.org/W3168545914","https://openalex.org/W3171463583","https://openalex.org/W3176507666","https://openalex.org/W3176624977","https://openalex.org/W3212219118","https://openalex.org/W3213132814","https://openalex.org/W4214717370","https://openalex.org/W4283800590","https://openalex.org/W4287756322","https://openalex.org/W4287811291","https://openalex.org/W4293469690"],"related_works":["https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W4306904969","https://openalex.org/W2004102934","https://openalex.org/W4366455350","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4],"been":[5,34],"a":[6,142],"promising":[7],"solution":[8],"to":[9,132,150,189],"many":[10],"complex":[11],"decision-making":[12],"problems.":[13,205],"Nevertheless,":[14],"the":[15,65,108,152,169,180,190],"notorious":[16],"weakness":[17],"in":[18,28,51,63,73,84,177,200],"generalization":[19],"among":[20],"environments":[21,74,85,160],"prevent":[22],"widespread":[23],"application":[24],"of":[25,157],"DRL":[26],"agents":[27],"real-world":[29],"scenarios.":[30],"Although":[31],"advances":[32],"have":[33],"made":[35],"recently,":[36],"most":[37],"prior":[38],"works":[39],"assume":[40],"sufficient":[41],"online":[42,81,165],"interaction":[43],"on":[44,59],"training":[45,106],"environments,":[46,179],"which":[47,64],"can":[48],"be":[49],"costly":[50],"practical":[52],"cases.":[53],"To":[54],"this":[55,90],"end,":[56],"we":[57,92],"focus":[58],"an":[60],"offline-training-online-adaptation":[61],"setting,":[62],"agent":[66],"first":[67],"learns":[68],"from":[69,161,173],"offline":[70,105,162],"experiences":[71,175],"collected":[72,176],"with":[75,86,96,168,187],"different":[76,155],"dynamics":[77],"and":[78,111,119,137,159],"then":[79],"performs":[80],"policy":[82,102,112,120,181,203],"adaptation":[83,166,204],"new":[87,178],"dynamics.":[88],"In":[89,104,164],"paper,":[91],"propose":[93],"Policy":[94],"Adaptation":[95],"Decoupled":[97],"Representations":[98],"(PAnDR)":[99],"for":[100,154],"fast":[101],"adaptation.":[103],"phase,":[107,167],"environment":[109,170],"representation":[110,113],"are":[114,125],"learned":[115,140],"through":[116],"contrastive":[117],"learning":[118],"recovery,":[121],"respectively.":[122],"The":[123],"representations":[124],"further":[126],"refined":[127],"by":[128,184],"mutual":[129],"information":[130],"optimization":[131],"make":[133],"them":[134],"more":[135],"decoupled":[136],"complete.":[138],"With":[139],"representations,":[141],"Policy-Dynamics":[143],"Value":[144],"Function":[145],"(PDVF)":[146],"network":[147],"is":[148,182],"trained":[149],"approximate":[151],"values":[153],"combinations":[156],"policies":[158],"experiences.":[163],"context":[171],"inferred":[172],"few":[174],"optimized":[183],"gradient":[185],"ascent":[186],"respect":[188],"PDVF.":[191],"Our":[192],"experiments":[193],"show":[194],"that":[195],"PAnDR":[196],"outperforms":[197],"existing":[198],"algorithms":[199],"several":[201],"representative":[202]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}