{"id":"https://openalex.org/W4225326866","doi":"https://doi.org/10.1109/icassp43922.2022.9746857","title":"Improving Actor-Critic Reinforcement Learning Via Hamiltonian Monte Carlo Method","display_name":"Improving Actor-Critic Reinforcement Learning Via Hamiltonian Monte Carlo Method","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225326866","doi":"https://doi.org/10.1109/icassp43922.2022.9746857"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101428767","display_name":"Duo Xu","orcid":"https://orcid.org/0000-0001-6195-3444"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Duo Xu","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,Atlanta,GA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,Atlanta,GA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083854532","display_name":"Faramarz Fekri","orcid":"https://orcid.org/0000-0001-5008-8803"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faramarz Fekri","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,Atlanta,GA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,Atlanta,GA,30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101428767"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55427463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"36","issue":null,"first_page":"4018","last_page":"4022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9211999773979187,"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/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9124000072479248,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8250583410263062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7243459820747375},{"id":"https://openalex.org/keywords/hamiltonian","display_name":"Hamiltonian (control theory)","score":0.5795974731445312},{"id":"https://openalex.org/keywords/amortization","display_name":"Amortization","score":0.5775363445281982},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5006649494171143},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4539896249771118},{"id":"https://openalex.org/keywords/hybrid-monte-carlo","display_name":"Hybrid Monte Carlo","score":0.4520830512046814},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4398340582847595},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4089434742927551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33303171396255493},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.20011553168296814},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19633761048316956}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8250583410263062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7243459820747375},{"id":"https://openalex.org/C130787639","wikidata":"https://www.wikidata.org/wiki/Q5645293","display_name":"Hamiltonian (control theory)","level":2,"score":0.5795974731445312},{"id":"https://openalex.org/C2781198434","wikidata":"https://www.wikidata.org/wiki/Q4064479","display_name":"Amortization","level":3,"score":0.5775363445281982},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5006649494171143},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4539896249771118},{"id":"https://openalex.org/C13153151","wikidata":"https://www.wikidata.org/wiki/Q1639846","display_name":"Hybrid Monte Carlo","level":4,"score":0.4520830512046814},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4398340582847595},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4089434742927551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33303171396255493},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.20011553168296814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19633761048316956},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C2777764128","wikidata":"https://www.wikidata.org/wiki/Q189539","display_name":"Loan","level":2,"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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1499798934","https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W1909320841","https://openalex.org/W2094342172","https://openalex.org/W2158782408","https://openalex.org/W2403726878","https://openalex.org/W2736601468","https://openalex.org/W2768847291","https://openalex.org/W2781726626","https://openalex.org/W2799151646","https://openalex.org/W2893470574","https://openalex.org/W2952264928","https://openalex.org/W2954040150","https://openalex.org/W2963218199","https://openalex.org/W2963267001","https://openalex.org/W2963722050","https://openalex.org/W2964043796","https://openalex.org/W2964168257","https://openalex.org/W2982238716","https://openalex.org/W3029541954","https://openalex.org/W3214009513","https://openalex.org/W4300537545","https://openalex.org/W6629687487","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6639732818","https://openalex.org/W6677929280","https://openalex.org/W6692846177","https://openalex.org/W6713578759","https://openalex.org/W6713603661","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747888389","https://openalex.org/W6748107402","https://openalex.org/W6749821205","https://openalex.org/W6750186571","https://openalex.org/W6755137159","https://openalex.org/W6763328670","https://openalex.org/W6767334564","https://openalex.org/W6784511220"],"related_works":["https://openalex.org/W4383753508","https://openalex.org/W2368911659","https://openalex.org/W2389141549","https://openalex.org/W3120663569","https://openalex.org/W2744359232","https://openalex.org/W2993322139","https://openalex.org/W2019030367","https://openalex.org/W2900980243","https://openalex.org/W607542326","https://openalex.org/W1604650444"],"abstract_inverted_index":{"The":[0],"actor-critic":[1,15,27,65,175],"RL":[2,16,28,66],"is":[3,70,167],"widely":[4],"used":[5],"in":[6,24,55],"various":[7],"robotic":[8],"control":[9,154],"tasks.":[10],"However,":[11],"by":[12,46],"viewing":[13],"the":[14,18,26,36,47,61,83,93,99,104,112,116,126,145,164],"from":[17,82],"perspective":[19],"of":[20,50,64,118,131],"variational":[21],"inference":[22],"(VI),":[23],"practice,":[25],"may":[29],"yield":[30],"suboptimal":[31],"policy":[32,62,85,94],"estimates":[33],"due":[34],"to":[35,59,79,87,96,115,143],"amortization":[37,105],"gap":[38],"and":[39,101,158,170],"insufficient":[40],"exploration.":[41],"In":[42],"this":[43],"work,":[44],"inspired":[45],"previous":[48,174],"use":[49],"Hamiltonian":[51,73,146],"Monte":[52],"Carlo":[53],"(HMC)":[54],"VI,":[56],"we":[57,77,137,161],"propose":[58,78,138],"integrate":[60],"network":[63],"with":[67,121],"HMC,":[68],"which":[69],"termed":[71],"as":[72],"Policy.":[74],"As":[75],"such":[76],"evolve":[80],"actions":[81],"base":[84],"according":[86],"HMC.":[88],"First,":[89],"HMC":[90,108,134],"can":[91,109],"improve":[92],"distribution":[95],"better":[97],"approximate":[98],"posterior":[100],"hence":[102],"reduce":[103],"gap.":[106],"Second,":[107],"also":[110],"guide":[111],"exploration":[113,127],"more":[114],"regions":[117],"action":[119],"spaces":[120],"higher":[122],"Q":[123],"values,":[124],"enhancing":[125],"efficiency.":[128],"Further,":[129],"instead":[130],"directly":[132],"applying":[133],"into":[135],"RL,":[136],"a":[139,168],"new":[140],"leapfrog":[141],"operator":[142],"simulate":[144],"dynamics.":[147],"With":[148],"comprehensive":[149],"empirical":[150],"experiments":[151],"on":[152],"continuous":[153],"baselines,":[155],"including":[156],"MuJoCo":[157],"PyBullet":[159],"Roboschool,":[160],"show":[162],"that":[163],"proposed":[165],"approach":[166],"data-efficient":[169],"easy-to-implement":[171],"improvement":[172],"over":[173],"methods.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}