{"id":"https://openalex.org/W2949649155","doi":"https://doi.org/10.1145/3292500.3330892","title":"Separated Trust Regions Policy Optimization Method","display_name":"Separated Trust Regions Policy Optimization Method","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2949649155","doi":"https://doi.org/10.1145/3292500.3330892","mag":"2949649155"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"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/A5060407895","display_name":"Luobao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luobao Zou","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029597701","display_name":"Zhiwei Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Zhuang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101927458","display_name":"Yin Cheng","orcid":"https://orcid.org/0000-0002-2822-9873"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Cheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024151369","display_name":"Xuechun Wang","orcid":"https://orcid.org/0000-0003-3931-566X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechun Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414775","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.50149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1471","last_page":"1479"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7074583768844604},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6678645610809326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6654440760612488},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6384657621383667},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5679272413253784},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5586957335472107},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.5478085279464722},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.5101414322853088},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4940824806690216},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4291863739490509},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4265786409378052},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4141181707382202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3626629710197449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22379806637763977},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2201421558856964},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19726014137268066},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.12371596693992615},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11850437521934509},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10801061987876892}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7074583768844604},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6678645610809326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654440760612488},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6384657621383667},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5679272413253784},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5586957335472107},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.5478085279464722},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.5101414322853088},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4940824806690216},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4291863739490509},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4265786409378052},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4141181707382202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3626629710197449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22379806637763977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2201421558856964},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19726014137268066},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.12371596693992615},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11850437521934509},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10801061987876892},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W64088143","https://openalex.org/W2107464055","https://openalex.org/W2130984546","https://openalex.org/W2145339207","https://openalex.org/W2172968643","https://openalex.org/W2257979135","https://openalex.org/W2612690371","https://openalex.org/W2998145016"],"related_works":["https://openalex.org/W2080108722","https://openalex.org/W2752681920","https://openalex.org/W1997473290","https://openalex.org/W2353911672","https://openalex.org/W2393042414","https://openalex.org/W4385488867","https://openalex.org/W4312713068","https://openalex.org/W2887199102","https://openalex.org/W4213452707","https://openalex.org/W3038556200"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,36,82],"propose":[4,37],"a":[5,38,61,121],"moderate":[6],"policy":[7,27,64,88,101,109],"update":[8,110],"method":[9],"for":[10,51,87,108,114],"reinforcement":[11],"learning,":[12],"which":[13,81],"encourages":[14],"the":[15,26,32,47,55,130,139,154],"agent":[16],"to":[17,99],"explore":[18],"more":[19,28,42,112],"boldly":[20],"in":[21,129],"early":[22],"episodes":[23],"but":[24,104,151],"updates":[25],"cautious.":[29],"Based":[30],"on":[31,120],"maximum":[33],"entropy":[34,59,65],"framework,":[35],"softer":[39],"objective":[40],"with":[41],"conservative":[43],"constraints":[44],"and":[45,90,111],"build":[46],"separated":[48,84],"trust":[49,85],"regions":[50],"optimization.":[52],"To":[53],"reduce":[54],"variance":[56,91],"of":[57,66,72,124,142],"expected":[58],"return,":[60],"calculated":[62],"state":[63,141],"Gaussian":[67],"distribution":[68],"is":[69,106],"preferred":[70],"instead":[71],"collecting":[73],"log":[74],"probability":[75],"by":[76],"sampling.":[77],"This":[78],"new":[79],"method,":[80],"call":[83],"region":[86],"mean":[89],"(STRMV),":[92],"can":[93],"be":[94],"view":[95],"as":[96],"an":[97],"extension":[98],"proximal":[100],"optimization":[102],"(PPO)":[103],"it":[105],"gentler":[107],"lively":[113],"exploration.":[115],"We":[116],"test":[117],"our":[118],"approach":[119],"wide":[122],"variety":[123],"continuous":[125],"control":[126],"benchmark":[127],"tasks":[128],"MuJoCo":[131],"environment.":[132],"The":[133],"experiments":[134],"demonstrate":[135],"that":[136],"STRMV":[137],"outperforms":[138],"previous":[140],"art":[143],"on-policy":[144],"methods,":[145],"not":[146],"only":[147],"achieving":[148],"higher":[149],"rewards":[150],"also":[152],"improving":[153],"sample":[155],"efficiency.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}