{"id":"https://openalex.org/W4414359365","doi":"https://doi.org/10.24963/ijcai.2025/556","title":"KIPPO: Koopman-Inspired Proximal Policy Optimization","display_name":"KIPPO: Koopman-Inspired Proximal Policy Optimization","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359365","doi":"https://doi.org/10.24963/ijcai.2025/556"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/556","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5046136367","display_name":"Andrei Cozma","orcid":"https://orcid.org/0009-0001-3670-0813"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrei Cozma","raw_affiliation_strings":["University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030126204","display_name":"Landon Harris","orcid":"https://orcid.org/0009-0004-7737-8914"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Landon Harris","raw_affiliation_strings":["University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111499496","display_name":"Hairong Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hairong Qi","raw_affiliation_strings":["University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11845298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4994","last_page":"5002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8141000270843506,"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":0.8141000270843506,"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/representation","display_name":"Representation (politics)","score":0.48159998655319214},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.46459999680519104},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4250999987125397},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4066999852657318},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4009999930858612},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863000154495239},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5572999715805054},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48159998655319214},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4388999938964844},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/556","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3,74],"made":[4],"significant":[5],"strides":[6],"in":[7,26,58],"various":[8,197],"domains,":[9],"and":[10,30,50,61,110],"policy":[11,142,159,169],"gradient":[12,59],"methods":[13,34],"like":[14],"Proximal":[15,120],"Policy":[16,121],"Optimization":[17,122],"(PPO)":[18],"have":[19],"gained":[20],"popularity":[21],"due":[22],"to":[23,67,112,156,192],"their":[24,101],"balance":[25],"performance,":[27],"training":[28],"stability,":[29],"computational":[31],"efficiency.":[32],"These":[33],"directly":[35],"optimize":[36],"policies":[37,45],"through":[38,84,147],"gradient-based":[39],"updates.":[40],"However,":[41],"developing":[42],"effective":[43,141],"control":[44,199],"for":[46,80,140],"environments":[47],"with":[48,100,183],"complex":[49],"non-linear":[51,82,102],"dynamics":[52,135],"remains":[53],"a":[54,77,92,148],"challenge.":[55],"High":[56],"variance":[57],"estimates":[60],"non-convex":[62],"optimization":[63,160],"landscapes":[64],"often":[65],"lead":[66],"unstable":[68],"learning":[69],"trajectories.":[70],"Koopman":[71],"Operator":[72],"Theory":[73],"emerged":[75],"as":[76],"powerful":[78],"framework":[79],"studying":[81],"systems":[83,105],"an":[85,126],"infinite-dimensional":[86],"linear":[87,104,128],"operator":[88],"that":[89,152],"acts":[90],"on":[91,196],"higher-dimensional":[93],"space":[94],"of":[95,131,166],"measurement":[96],"functions.":[97],"In":[98,114],"contrast":[99],"counterparts,":[103],"are":[106],"simpler,":[107],"more":[108],"predictable,":[109],"easier":[111],"analyze.":[113],"this":[115],"paper,":[116],"we":[117],"present":[118],"Koopman-Inspired":[119],"(KIPPO),":[123],"which":[124],"learns":[125],"approximately":[127],"latent-space":[129],"representation":[130],"the":[132,157,164,167,180],"underlying":[133],"system\u2019s":[134],"while":[136,187],"retaining":[137],"essential":[138],"features":[139],"learning.":[143],"This":[144],"is":[145],"achieved":[146],"Koopman-approximation":[149],"auxiliary":[150],"network":[151],"can":[153],"be":[154],"added":[155],"baseline":[158,182],"algorithms":[161],"without":[162],"altering":[163],"architecture":[165],"core":[168],"or":[170],"value":[171],"function.":[172],"Extensive":[173],"experimental":[174],"results":[175],"demonstrate":[176],"consistent":[177],"improvements":[178],"over":[179],"PPO":[181],"6\u201360%":[184],"increased":[185],"performance":[186],"reducing":[188],"variability":[189],"by":[190],"up":[191],"91%":[193],"when":[194],"evaluated":[195],"continuous":[198],"tasks.":[200]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}