{"id":"https://openalex.org/W4385488677","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191507","title":"Policy Optimization with Augmented Value Targets for Generalization in Reinforcement Learning","display_name":"Policy Optimization with Augmented Value Targets for Generalization in Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488677","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191507"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191507","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191507","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191507","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"volume":null,"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/A5004876535","display_name":"Nasik Muhammad Nafi","orcid":"https://orcid.org/0000-0002-8492-9217","observed_orcids":["https://orcid.org/0000-0002-8492-9217"]},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasik Muhammad Nafi","raw_affiliation_strings":["Kansas State University,Department of Computer Science,Manhattan,KS,USA","Department of Computer Science, Kansas State University, Manhattan, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University,Department of Computer Science,Manhattan,KS,USA","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092582456","display_name":"Giovanni Poggi-Corradini","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giovanni Poggi-Corradini","raw_affiliation_strings":["Kansas State University,Department of Computer Science,Manhattan,KS,USA","Department of Computer Science, Kansas State University, Manhattan, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University,Department of Computer Science,Manhattan,KS,USA","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016291944","display_name":"William W.Y. Hsu","orcid":"https://orcid.org/0000-0002-5168-070X","observed_orcids":["https://orcid.org/0000-0002-5168-070X"]},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hsu","raw_affiliation_strings":["Kansas State University,Department of Computer Science,Manhattan,KS,USA","Department of Computer Science, Kansas State University, Manhattan, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University,Department of Computer Science,Manhattan,KS,USA","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":0.1775,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36618226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/policy-optimization","display_name":"policy optimization","score":0.6880000233650208},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.675000011920929},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8140000104904175},{"id":"https://openalex.org/keywords/procgen","display_name":"Procgen","score":0.8370000123977661},{"id":"https://openalex.org/keywords/crafters","display_name":"crafters","score":0.7929999828338623},{"id":"https://openalex.org/keywords/unknown-environments","display_name":"unknown environments","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8948094248771667},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.817009687423706},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7932167053222656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760749101638794},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6273672580718994},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6180114150047302},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6013311147689819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507073998451233},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5468990802764893},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5446538329124451},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40378037095069885},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39256423711776733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17005985975265503},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191507","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191507","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191507","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2593658277","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2786036274","https://openalex.org/W2891790128","https://openalex.org/W2893662673","https://openalex.org/W2898436992","https://openalex.org/W2903181768","https://openalex.org/W2970214542","https://openalex.org/W2994073215","https://openalex.org/W3023640063","https://openalex.org/W3035595221","https://openalex.org/W3035672869","https://openalex.org/W3036670859","https://openalex.org/W3039141380","https://openalex.org/W3092744199","https://openalex.org/W3103999165","https://openalex.org/W3119908121","https://openalex.org/W3129741749","https://openalex.org/W3169036355","https://openalex.org/W3175966482","https://openalex.org/W3197485521","https://openalex.org/W3201036908","https://openalex.org/W4223980304","https://openalex.org/W4281554051","https://openalex.org/W4283712742","https://openalex.org/W4360764658","https://openalex.org/W4402352219","https://openalex.org/W6741002519","https://openalex.org/W6810212583","https://openalex.org/W6838876373","https://openalex.org/W6871363104","https://openalex.org/W7133186840"],"related_works":["https://openalex.org/W7124245675","https://openalex.org/W3214048558","https://openalex.org/W7133186840","https://openalex.org/W3036670859","https://openalex.org/W3175966482","https://openalex.org/W4360764546","https://openalex.org/W3166968915","https://openalex.org/W4386346170","https://openalex.org/W4360764658","https://openalex.org/W4206848870"],"abstract_inverted_index":{"Our":[0],"work":[1],"aims":[2],"to":[3,29,76,82],"improve":[4],"the":[5,39,47,60,70,72,77,83,103,111,115,124,127,141,155,164,178,191],"generalization":[6,31],"performance":[7],"of":[8,69,105,117,126,190],"a":[9,66],"reinforcement":[10],"learning":[11,64],"(RL)":[12],"agent":[13,73],"in":[14,22,53,55,153,188],"unseen":[15,159],"environment":[16],"variations.":[17],"The":[18],"value":[19,61,78,99,112,156],"function":[20,100,113],"used":[21],"RL":[23],"agents":[24],"is":[25,43,130,151],"frequently":[26],"overfitted,":[27],"leading":[28],"poor":[30],"performance.":[32],"In":[33],"this":[34,88],"work,":[35],"we":[36,90],"argue":[37],"that":[38,80,122,147,184],"task":[40],"completion":[41],"time":[42],"highly":[44],"impacted":[45],"by":[46],"varying":[48],"environmental":[49],"conditions,":[50],"thus":[51],"resulting":[52],"variation":[54,68,108],"episode":[56,85,106],"lengths,":[57],"and":[58,109,143,161,175],"consequently,":[59],"estimation.":[62],"Therefore,":[63],"from":[65,193],"limited":[67],"environments,":[71],"gets":[74],"biased":[75],"estimates":[79,157],"correspond":[81],"observed":[84],"lengths.":[86],"To":[87],"end,":[89],"introduce":[91],"Augmented":[92],"Value":[93],"Targets":[94],"(AVaTar),":[95],"which":[96],"generates":[97],"multiple":[98],"targets":[101,129],"considering":[102],"possibility":[104],"length":[107],"optimizes":[110],"with":[114,177],"average":[116,125],"these":[118],"targets.":[119],"We":[120],"demonstrate":[121],"optimizing":[123],"augmented":[128],"computationally":[131],"more":[132],"feasible":[133],"than":[134],"independently":[135],"leveraging":[136],"those":[137],"pseudotargets.":[138],"Evaluations":[139],"on":[140],"Procgen":[142],"Crafter":[144],"benchmark":[145],"show":[146],"our":[148],"proposed":[149],"approach":[150,181],"effective":[152],"generalizing":[154],"over":[158],"contexts":[160],"significantly":[162],"outperforms":[163,186],"standard":[165],"policy":[166],"gradient":[167],"algorithm":[168],"Proximal":[169],"Policy":[170],"Optimization":[171],"(PPO).":[172],"Furthermore,":[173],"comparison":[174],"integration":[176],"recent":[179],"generalizationspecific":[180],"UCB-DrAC":[182,187],"indicate":[183],"AVaTar":[185],"most":[189],"environments":[192],"Procgen.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2023-08-03T00:00:00"}