{"id":"https://openalex.org/W4385767661","doi":"https://doi.org/10.24963/ijcai.2023/51","title":"Robust Reinforcement Learning via Progressive Task Sequence","display_name":"Robust Reinforcement Learning via Progressive Task Sequence","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767661","doi":"https://doi.org/10.24963/ijcai.2023/51"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/51","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/51","pdf_url":"https://www.ijcai.org/proceedings/2023/0051.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0051.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045240151","display_name":"Yike Li","orcid":"https://orcid.org/0000-0002-6693-0935"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yike Li","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007332382","display_name":"Yunzhe Tian","orcid":"https://orcid.org/0000-0003-0015-7780"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhe Tian","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085778638","display_name":"Endong Tong","orcid":"https://orcid.org/0000-0003-0348-2108"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Endong Tong","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047248381","display_name":"Wenjia Niu","orcid":"https://orcid.org/0000-0003-4706-4266"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjia Niu","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108529463","display_name":"Jiqiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqiang Liu","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045240151"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.5139,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71367974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9821000099182129,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8388309478759766},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8212952017784119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7515236735343933},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5927943587303162},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5393611788749695},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5047081708908081},{"id":"https://openalex.org/keywords/robust-optimization","display_name":"Robust optimization","score":0.4902651607990265},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.481249064207077},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4685191810131073},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46028509736061096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43046319484710693},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3260805010795593},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22745710611343384},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14933985471725464},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07159233093261719}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8388309478759766},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8212952017784119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515236735343933},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5927943587303162},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5393611788749695},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5047081708908081},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.4902651607990265},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.481249064207077},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4685191810131073},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46028509736061096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43046319484710693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3260805010795593},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22745710611343384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14933985471725464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07159233093261719},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/51","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/51","pdf_url":"https://www.ijcai.org/proceedings/2023/0051.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/51","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/51","pdf_url":"https://www.ijcai.org/proceedings/2023/0051.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1306871517","display_name":null,"funder_award_id":"2020YFB1005604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2751604336","display_name":null,"funder_award_id":"2020YFB2103802","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2983795295","display_name":null,"funder_award_id":"61802389","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3756677140","display_name":null,"funder_award_id":"2020YFB2103802","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3777689131","display_name":null,"funder_award_id":"B21038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4956937160","display_name":null,"funder_award_id":"61972025","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5441832261","display_name":null,"funder_award_id":"61802389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5517038434","display_name":null,"funder_award_id":"2020YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5858129093","display_name":null,"funder_award_id":"61972025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6759679500","display_name":null,"funder_award_id":"2020YFB1005604","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6927212374","display_name":null,"funder_award_id":"61802389","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6993104196","display_name":null,"funder_award_id":"2020YFB10056","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7168417614","display_name":null,"funder_award_id":"61972025","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G767198619","display_name":null,"funder_award_id":"2020YFB1005604","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767661.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1487751794","https://openalex.org/W1771410628","https://openalex.org/W1965878388","https://openalex.org/W1977023370","https://openalex.org/W2151509918","https://openalex.org/W2155153696","https://openalex.org/W2158782408","https://openalex.org/W2168565265","https://openalex.org/W2602963933","https://openalex.org/W2766447205","https://openalex.org/W2788883687","https://openalex.org/W2914994663","https://openalex.org/W2940572873","https://openalex.org/W2966684444","https://openalex.org/W2982095652","https://openalex.org/W3100975812","https://openalex.org/W3101442004","https://openalex.org/W3110161557","https://openalex.org/W3115362515","https://openalex.org/W3130610232","https://openalex.org/W3139434095","https://openalex.org/W3170872007","https://openalex.org/W3174920238","https://openalex.org/W3213432714","https://openalex.org/W3214274533","https://openalex.org/W4225976865","https://openalex.org/W4286891527","https://openalex.org/W4287117147","https://openalex.org/W4287328532","https://openalex.org/W4288374418","https://openalex.org/W4298101950","https://openalex.org/W4301602852","https://openalex.org/W4306177393","https://openalex.org/W4311565450","https://openalex.org/W4312829939"],"related_works":["https://openalex.org/W2002696586","https://openalex.org/W2793423758","https://openalex.org/W3149055374","https://openalex.org/W2053131036","https://openalex.org/W2216231335","https://openalex.org/W3195104199","https://openalex.org/W4386254288","https://openalex.org/W4292572523","https://openalex.org/W2809352861","https://openalex.org/W2056349093"],"abstract_inverted_index":{"Robust":[0],"reinforcement":[1],"learning":[2,158],"(RL)":[3],"has":[4],"been":[5],"a":[6,29,89,114,130],"challenging":[7],"problem":[8,26,74],"due":[9],"to":[10,36,51,97,118,138,159],"the":[11,16,23,38,42,46,62,85,94,104,108,120,127,147,161,165,173,180],"gap":[12],"between":[13],"simulation":[14],"and":[15,65,79,107,133,164,184],"real":[17],"world.":[18],"Existing":[19],"efforts":[20],"typically":[21],"address":[22],"robust":[24,86],"RL":[25,87],"by":[27],"solving":[28],"max-min":[30],"problem.":[31],"The":[32],"main":[33],"idea":[34],"is":[35,96,136],"maximize":[37],"cumulative":[39],"reward":[40],"under":[41,102],"worst-possible":[43],"perturbations.":[44],"However,":[45],"worst-case":[47],"optimization":[48,91],"either":[49],"leads":[50],"overly":[52],"conservative":[53],"solutions":[54],"or":[55],"unstable":[56],"training":[57,166],"process,":[58],"which":[59],"further":[60],"affects":[61],"policy":[63,101,162],"robustness":[64,163],"generalization":[66],"performance.":[67],"In":[68],"this":[69,73],"paper,":[70],"we":[71,83,112],"tackle":[72],"from":[75],"both":[76,103],"formulation":[77],"definition":[78,125],"algorithm":[80],"design.":[81],"First,":[82],"formulate":[84],"as":[88],"max-expectation":[90,121],"problem,":[92],"where":[93],"goal":[95],"find":[98],"an":[99],"optimal":[100],"worst":[105],"cases":[106],"non-worst":[109],"cases.":[110],"Then,":[111],"propose":[113],"novel":[115],"framework":[116],"DRRL":[117,154],"solve":[119],"optimization.":[122],"Given":[123],"our":[124],"of":[126],"feasible":[128],"tasks,":[129,153],"task":[131],"generation":[132],"sequencing":[134],"mechanism":[135],"introduced":[137],"dynamically":[139],"output":[140],"tasks":[141],"at":[142],"appropriate":[143],"difficulty":[144],"level":[145],"for":[146],"current":[148],"policy.":[149],"With":[150],"these":[151],"progressive":[152],"realizes":[155],"dynamic":[156],"multi-task":[157],"improve":[160],"stability.":[167],"Finally,":[168],"extensive":[169],"experiments":[170],"demonstrate":[171],"that":[172],"proposed":[174],"method":[175],"exhibits":[176],"significant":[177],"performance":[178],"on":[179],"unmanned":[181],"CarRacing":[182],"game":[183],"multiple":[185],"high-dimensional":[186],"MuJoCo":[187],"environments.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}