{"id":"https://openalex.org/W4414247644","doi":"https://doi.org/10.1145/3719545.3721109","title":"InPTR: Integration Prioritized Trajectory Replay","display_name":"InPTR: Integration Prioritized Trajectory Replay","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4414247644","doi":"https://doi.org/10.1145/3719545.3721109"},"language":"en","primary_location":{"id":"doi:10.1145/3719545.3721109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719545.3721109","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3721109","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3721109","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047295323","display_name":"Chendie Yao","orcid":"https://orcid.org/0000-0003-4652-9594"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chendie Yao","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4652-9594","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080249769","display_name":"Xingxing Liang","orcid":"https://orcid.org/0000-0002-3594-2167"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Liang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3594-2167","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060298026","display_name":"Longfei Zhang","orcid":"https://orcid.org/0000-0001-8259-5148"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longfei Zhang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8259-5148","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115467769","display_name":"Jincai Huang","orcid":"https://orcid.org/0000-0003-2937-3065"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincai Huang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2937-3065","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090553770","display_name":"Jun Lei","orcid":"https://orcid.org/0000-0003-2354-7618"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lei","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2354-7618","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yulong Zhang","orcid":"https://orcid.org/0000-0002-2353-1416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulong Zhang","raw_affiliation_strings":["31002 Unit, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2353-1416","affiliations":[{"raw_affiliation_string":"31002 Unit, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4509,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64236111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10142","display_name":"Formal Methods in Verification","score":0.9944999814033508,"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/trajectory","display_name":"Trajectory","score":0.7096999883651733},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6642000079154968},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5817999839782715},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5224000215530396},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5063999891281128},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4884999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746999859809875},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7096999883651733},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.32190001010894775},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3719545.3721109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719545.3721109","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3721109","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3719545.3721109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719545.3721109","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3721109","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3806275285","display_name":null,"funder_award_id":"72301289","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/W4414247644.pdf","grobid_xml":"https://content.openalex.org/works/W4414247644.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2766447205","https://openalex.org/W2775482448","https://openalex.org/W2976021111","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W3002044607","https://openalex.org/W3102339132","https://openalex.org/W3113358868","https://openalex.org/W3118210634","https://openalex.org/W4214717370"],"related_works":[],"abstract_inverted_index":{"On-policy":[0],"deep":[1],"reinforcement":[2,183],"learning":[3,184],"algorithms":[4,185],"have":[5],"low":[6],"data":[7,17,29,60],"utilization":[8],"and":[9,36,54,89,111,165,187],"require":[10],"significant":[11],"experience":[12,48],"for":[13,114],"policy":[14,22,35,65,70,116,154],"improvement.Reusing":[15],"important":[16],"generated":[18,59],"by":[19,128],"an":[20],"old":[21],"can":[23],"both":[24],"increase":[25],"the":[26,33,38,42,45,55,62,93,98,103,124,136,147,153,156,161,181,190],"amount":[27],"of":[28,47,58,64,86,95,138,155,163,170,193],"needed":[30],"to":[31,40,51,91,122,151],"update":[32],"current":[34,43],"enhance":[37],"ability":[39],"improve":[41],"policy.However,":[44],"importance":[46,94,109,130],"is":[49],"difficult":[50],"measure":[52,92],"effectively":[53,195],"direct":[56],"use":[57],"increases":[61],"variance":[63,126],"improvement.We":[66],"propose":[67],"a":[68,79,143,168],"proximal":[69],"optimization":[71],"algorithm":[72,105],"with":[73],"integration":[74],"prioritized":[75,99],"trajectory":[76,100],"replay":[77,101],"(InPTR),":[78],"method":[80,179],"that":[81,177],"designs":[82],"three":[83,139,157],"priority":[84,140,158],"metrics":[85,141],"max,":[87],"mean":[88],"reward":[90],"trajectories.We":[96],"incorporate":[97],"into":[102],"PPO":[104,115,186],"(PTR-PPO)":[106],"where":[107],"truncated":[108],"weight":[110],"loss":[112],"function":[113],"improvement":[117],"under":[118,132,189],"off-policy":[119],"are":[120],"introduced":[121],"overcome":[123],"high":[125],"caused":[127],"large":[129],"weights":[131],"multi-step":[133],"experience.To":[134],"trade-off":[135],"performance":[137,162],"in":[142,167],"task,":[144],"we":[145],"design":[146],"learner":[148],"selection":[149],"module":[150],"integrate":[152],"metrics.We":[159],"evaluate":[160],"InPTR":[164],"PTR-PPO":[166],"set":[169],"Atari":[171],"discrete":[172],"control":[173],"tasks.The":[174],"results":[175],"show":[176],"our":[178],"outperforms":[180],"mainstream":[182],"ACER":[188],"same":[191],"size":[192],"experience,":[194],"improving":[196],"sample":[197],"efficiency.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}