{"id":"https://openalex.org/W4392902663","doi":"https://doi.org/10.1109/icassp48485.2024.10447775","title":"P2DT: Mitigating Forgetting in Task-Incremental Learning with Progressive Prompt Decision Transformer","display_name":"P2DT: Mitigating Forgetting in Task-Incremental Learning with Progressive Prompt Decision Transformer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902663","doi":"https://doi.org/10.1109/icassp48485.2024.10447775"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100462284","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0000-0002-1811-7835"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","Tsinghua Shenzhen International Graduate School, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084153521","display_name":"Bokui Chen","orcid":"https://orcid.org/0000-0002-4947-5619"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bokui Chen","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China","Peng Cheng Laboratory, Shenzhen, China","Tsinghua Shenzhen International Graduate School, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100462284"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I4210152380","https://openalex.org/I4401726822","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61639388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7265","last_page":"7269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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/forgetting","display_name":"Forgetting","score":0.9507226943969727},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8265979290008545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692112922668457},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7339608669281006},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6027570962905884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5368452668190002},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42583560943603516},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1510208249092102},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.07300516963005066},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06289711594581604}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.9507226943969727},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8265979290008545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692112922668457},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7339608669281006},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6027570962905884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368452668190002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42583560943603516},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1510208249092102},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.07300516963005066},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06289711594581604},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2424347275","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2788388592","https://openalex.org/W2947150733","https://openalex.org/W2964189064","https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3033324992","https://openalex.org/W3097816393","https://openalex.org/W3169291081","https://openalex.org/W4205991051","https://openalex.org/W4281663178","https://openalex.org/W4295883599","https://openalex.org/W4385767986","https://openalex.org/W4386763940","https://openalex.org/W6741087337","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6796289742","https://openalex.org/W6810745647","https://openalex.org/W6838931476","https://openalex.org/W6849091572"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4248896073","https://openalex.org/W2974871044"],"abstract_inverted_index":{"Catastrophic":[0],"forgetting":[1,61,103],"poses":[2],"a":[3,12,29,42],"substantial":[4],"challenge":[5],"for":[6],"managing":[7],"intelligent":[8],"agents":[9,20],"controlled":[10],"by":[11,45],"large":[13],"model,":[14],"causing":[15],"performance":[16],"degradation":[17],"when":[18],"these":[19],"face":[21],"new":[22,51,83],"tasks.":[23],"In":[24],"our":[25,98],"work,":[26],"we":[27],"propose":[28],"novel":[30],"solution":[31],"-":[32],"the":[33],"Progressive":[34],"Prompt":[35],"Decision":[36],"Transformer":[37],"(P2DT).":[38],"This":[39],"method":[40],"enhances":[41],"transformer-based":[43],"model":[44,99],"dynamically":[46],"appending":[47],"decision":[48],"tokens":[49,85],"during":[50,86],"task":[52,109],"training,":[53,87],"thus":[54],"fostering":[55],"task-specific":[56],"policies.":[57],"Our":[58],"approach":[59],"mitigates":[60],"in":[62],"continual":[63],"and":[64,81,104],"offline":[65],"reinforcement":[66,76],"learning":[67,77],"scenarios.":[68],"Moreover,":[69],"P2DT":[70],"leverages":[71],"trajectories":[72],"collected":[73],"via":[74],"traditional":[75],"from":[78,91],"all":[79],"tasks":[80],"generates":[82],"taskspecific":[84],"thereby":[88],"retaining":[89],"knowledge":[90],"previous":[92],"studies.":[93],"Preliminary":[94],"results":[95],"demonstrate":[96],"that":[97],"effectively":[100],"alleviates":[101],"catastrophic":[102],"scales":[105],"well":[106],"with":[107],"increasing":[108],"environments.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}