{"id":"https://openalex.org/W7095522086","doi":null,"title":"Author manuscript, published in \"American Control Conference (2012)\" Model-Free Reinforcement Learning with Continuous Action in Practice","display_name":"Author manuscript, published in \"American Control Conference (2012)\" Model-Free Reinforcement Learning with Continuous Action in Practice","alternate_titles":[],"publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7095522086"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.370.753","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/76/42/81/PDF/DegrisACC2012.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7095522086"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5026582515","display_name":"Thomas Degris","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Degris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058237113","display_name":"Patrick M. Pilarski","orcid":"https://orcid.org/0000-0003-1686-2978","observed_orcids":["https://orcid.org/0000-0003-1686-2978"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick M. Pilarski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Richard S. Sutton","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard S. Sutton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":true,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10320","display_name":"Neural Networks and Applications","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/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/continuous-actions","display_name":"continuous actions","score":0.8169999718666077},{"id":"https://openalex.org/keywords/actor-critic","display_name":"actor-critic","score":0.8519999980926514},{"id":"https://openalex.org/keywords/eligibility-traces","display_name":"eligibility traces","score":0.824999988079071},{"id":"https://openalex.org/keywords/gradient-scaling","display_name":"gradient scaling","score":0.9639999866485596},{"id":"https://openalex.org/keywords/real-time-learning","display_name":"real-time learning","score":0.6420000195503235},{"id":"https://openalex.org/keywords/robot-adaptation","display_name":"robot adaptation","score":0.6840000152587891}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8199999928474426},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6531999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863999724388123},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.569599986076355},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48539999127388},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.370.753","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/76/42/81/PDF/DegrisACC2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2024390895","https://openalex.org/W4301745725","https://openalex.org/W2113501460","https://openalex.org/W1585546346","https://openalex.org/W1574246016","https://openalex.org/W2268920910","https://openalex.org/W2101539915","https://openalex.org/W7099204643","https://openalex.org/W7007777517"],"abstract_inverted_index":{"Abstract":[0],"\u2014":[1],"Reinforcement":[2],"learning":[3],"methods":[4,47,71],"are":[5,36],"often":[6,54],"considered":[7],"as":[8],"a":[9,14,32,43,50,56,74,111,128,132],"potential":[10],"solution":[11],"to":[12,16,18,23,67,72,92,125],"enable":[13],"robot":[15],"adapt":[17],"changes":[19],"in":[20],"real":[21],"time":[22],"an":[24,97],"unpredictable":[25],"environment.":[26],"However,":[27],"with":[28,55,131],"continuous":[29,105],"action,":[30],"only":[31],"few":[33],"existing":[34,88],"algorithms":[35,91,103],"practical":[37,77],"for":[38],"real-time":[39],"learning.":[40],"In":[41],"such":[42,69],"setting,":[44],"most":[45],"effective":[46],"have":[48],"used":[49],"parameterized":[51,58],"policy":[52],"structure,":[53],"separate":[57],"value":[59],"function.":[60],"The":[61],"goal":[62],"of":[63,87,100,110],"this":[64],"paper":[65],"is":[66],"assess":[68],"actor\u2013critic":[70,123],"form":[73],"fully":[75],"specified":[76],"algorithm.":[78],"Our":[79],"specific":[80],"contributions":[81],"include":[82],"1)":[83],"developing":[84],"the":[85,101,108],"extension":[86],"incremental":[89],"policy-gradient":[90],"use":[93],"eligibility":[94],"traces,":[95],"2)":[96],"empirical":[98],"comparison":[99],"resulting":[102],"using":[104],"actions,":[106],"3)":[107],"evaluation":[109],"gradient-scaling":[112],"technique":[113],"that":[114],"can":[115],"significantly":[116],"improve":[117],"performance.":[118],"Finally,":[119],"we":[120],"apply":[121],"our":[122],"algorithm":[124],"learn":[126],"on":[127],"robotic":[129],"platform":[130]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7095522086","counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-10-27T00:00:00"}
