{"id":"https://openalex.org/W2965050397","doi":"https://doi.org/10.24963/ijcai.2019/434","title":"On Principled Entropy Exploration in Policy Optimization","display_name":"On Principled Entropy Exploration in Policy Optimization","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965050397","doi":"https://doi.org/10.24963/ijcai.2019/434","mag":"2965050397"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/434","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/434","pdf_url":"https://www.ijcai.org/proceedings/2019/0434.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/2019/0434.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014823249","display_name":"Jincheng Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jincheng Mei","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026521600","display_name":"Chenjun Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chenjun Xiao","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091647227","display_name":"Ruitong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162562","display_name":"Borealis (Austria)","ror":"https://ror.org/05eat3g39","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210162562"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ruitong Huang","raw_affiliation_strings":["Borealis AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Borealis AI Lab","institution_ids":["https://openalex.org/I4210162562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010575626","display_name":"Dale Schuurmans","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dale Schuurmans","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010677076","display_name":"Martin M\u0081\u00fcller","orcid":"https://orcid.org/0000-0002-5639-5318"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin M\u00fcller","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8799,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89433746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3130","last_page":"3136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9934999942779541,"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":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.7116949558258057},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6694762706756592},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5975629091262817},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5966989398002625},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5658243298530579},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5489242672920227},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4898495376110077},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.48725834488868713},{"id":"https://openalex.org/keywords/constrained-optimization-problem","display_name":"Constrained optimization problem","score":0.45765459537506104},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.420421838760376},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.4153049886226654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21364033222198486},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14676952362060547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12045213580131531},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10167932510375977},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09997987747192383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116949558258057},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6694762706756592},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5975629091262817},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5966989398002625},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5658243298530579},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5489242672920227},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4898495376110077},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.48725834488868713},{"id":"https://openalex.org/C2989514635","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization problem","level":3,"score":0.45765459537506104},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.420421838760376},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.4153049886226654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21364033222198486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14676952362060547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12045213580131531},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10167932510375977},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09997987747192383},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/434","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/434","pdf_url":"https://www.ijcai.org/proceedings/2019/0434.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/434","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/434","pdf_url":"https://www.ijcai.org/proceedings/2019/0434.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965050397.pdf","grobid_xml":"https://content.openalex.org/works/W2965050397.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W314779054","https://openalex.org/W1499669280","https://openalex.org/W1503398984","https://openalex.org/W1771410628","https://openalex.org/W1993411524","https://openalex.org/W2012587148","https://openalex.org/W2016384870","https://openalex.org/W2111967991","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2508728158","https://openalex.org/W2593044849","https://openalex.org/W2609650878","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2787938642","https://openalex.org/W2799151646","https://openalex.org/W2949561945","https://openalex.org/W2951507724","https://openalex.org/W2953220522","https://openalex.org/W2963267001","https://openalex.org/W2963622280","https://openalex.org/W2963630259","https://openalex.org/W2963849886","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W4297814233","https://openalex.org/W4301230920","https://openalex.org/W4301435544","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2142844925","https://openalex.org/W2513211214","https://openalex.org/W4240964608","https://openalex.org/W2085577866","https://openalex.org/W1994436307","https://openalex.org/W2198098822","https://openalex.org/W2022485595","https://openalex.org/W2355999325","https://openalex.org/W4312614571","https://openalex.org/W2170850735"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"Exploratory":[5],"Conservative":[6],"Policy":[7],"Optimization":[8],"(ECPO),":[9],"a":[10,23,32,91],"policy":[11,66,87],"optimization":[12,88],"strategy":[13],"that":[14,71],"improves":[15,76],"exploration":[16,30,78],"behavior":[17,49],"while":[18,57],"assuring":[19],"monotonic":[20],"progress":[21],"in":[22,90],"principled":[24],"objective.":[25],"ECPO":[26],"conducts":[27],"maximum":[28],"entropy":[29],"within":[31],"mirror":[33],"descent":[34],"framework,":[35],"but":[36],"updates":[37],"policies":[38],"using":[39],"reversed":[40],"KL":[41],"projection.":[42],"This":[43],"formulation":[44],"bypasses":[45],"undesirable":[46],"mode":[47],"seeking":[48],"and":[50,79],"avoids":[51],"premature":[52],"convergence":[53],"to":[54],"sub-optimal":[55],"policies,":[56],"still":[58],"supporting":[59],"strong":[60],"theoretical":[61],"properties":[62],"such":[63],"as":[64],"guaranteed":[65],"improvement.":[67],"Experimental":[68],"evaluations":[69],"demonstrate":[70],"the":[72,81],"proposed":[73],"method":[74],"significantly":[75],"practical":[77],"surpasses":[80],"empirical":[82],"performance":[83],"of":[84,93],"state-of-the":[85],"art":[86],"methods":[89],"set":[92],"benchmark":[94],"tasks.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}