{"id":"https://openalex.org/W3115641986","doi":"https://doi.org/10.1109/ssci47803.2020.9308175","title":"The True Online Continuous Learning Automation (TOCLA) in a continuous control benchmarking of actor-critic algorithms","display_name":"The True Online Continuous Learning Automation (TOCLA) in a continuous control benchmarking of actor-critic algorithms","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3115641986","doi":"https://doi.org/10.1109/ssci47803.2020.9308175","mag":"3115641986"},"language":"en","primary_location":{"id":"doi:10.1109/ssci47803.2020.9308175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5075841843","display_name":"Gordon Frost","orcid":null},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Gordon Frost","raw_affiliation_strings":["The School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UK","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014979931","display_name":"Marta Vallejo","orcid":"https://orcid.org/0000-0001-9957-954X"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marta Vallejo","raw_affiliation_strings":["The School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UK","institution_ids":["https://openalex.org/I32062511"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075841843"],"corresponding_institution_ids":["https://openalex.org/I32062511"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17758332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"266","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9343000054359436,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9261999726295471,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7840667963027954},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7169286608695984},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6935744881629944},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6593374609947205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6315117478370667},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5442355871200562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4857500195503235},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4661589562892914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4379347562789917},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3353804349899292},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33388596773147583},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16628488898277283},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16524013876914978}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7840667963027954},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7169286608695984},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6935744881629944},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6593374609947205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315117478370667},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5442355871200562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4857500195503235},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4661589562892914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4379347562789917},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3353804349899292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33388596773147583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16628488898277283},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16524013876914978},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci47803.2020.9308175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W55051199","https://openalex.org/W62791640","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1590684588","https://openalex.org/W1706571876","https://openalex.org/W2100677568","https://openalex.org/W2101539915","https://openalex.org/W2113913482","https://openalex.org/W2125074935","https://openalex.org/W2142183404","https://openalex.org/W2155027007","https://openalex.org/W2221586755","https://openalex.org/W2312609093","https://openalex.org/W2518491366","https://openalex.org/W2588566021","https://openalex.org/W2620853660","https://openalex.org/W2943490696","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4253978526","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6678545291","https://openalex.org/W6681218740","https://openalex.org/W6683204974","https://openalex.org/W6688755588","https://openalex.org/W6739308789","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4399363378","https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,22],"problems":[2],"are":[3,27],"often":[4],"discretised,":[5],"use":[6],"linear":[7],"function":[8,54],"approximation,":[9],"or":[10,36],"perform":[11],"batch":[12],"updates.":[13],"However,":[14],"many":[15],"applications":[16],"that":[17],"can":[18],"benefit":[19],"from":[20,103],"reinforcement":[21],"contain":[23],"continuous":[24],"variables":[25],"and":[26,68,76,152],"inherently":[28],"non-linear,":[29],"for":[30,51],"example,":[31],"the":[32,61,65,98,114,119,129,143],"control":[33],"of":[34,131,135],"aerospace":[35],"maritime":[37],"robotic":[38],"vehicles.":[39],"Recent":[40],"work":[41],"has":[42],"brought":[43],"focus":[44],"onto":[45],"online":[46],"temporal":[47],"difference":[48],"methods,":[49],"specifically":[50],"using":[52],"non-linear":[53],"approximation.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"evaluate":[60,77],"Forward":[62,120,144],"Actor-Critic":[63,70],"against":[64],"regular":[66],"Actor-Critic,":[67],"Continuous":[69,84,147],"Learning":[71,85,150],"Automation.":[72],"We":[73],"also":[74],"propose":[75],"a":[78,108],"new":[79],"algorithm":[80],"called":[81],"True":[82],"Online":[83],"Automation":[86],"(TOCLA)":[87],"which":[88,106],"combines":[89],"these":[90],"two":[91],"approaches.":[92],"The":[93],"chosen":[94],"benchmark":[95,115],"problem":[96],"was":[97],"Mountain":[99],"Car":[100],"Continuous-vO":[101],"environment":[102],"OpenAI":[104],"Gym,":[105],"represents":[107],"further":[109],"step":[110],"in":[111,123,133],"complexity":[112],"over":[113],"used":[116],"to":[117,138],"test":[118],"Actor":[121,145,148,153],"Critic":[122,149,154],"previous":[124],"works.":[125],"Our":[126],"results":[127],"demonstrate":[128],"superiority":[130],"TOCLA":[132],"terms":[134],"its":[136],"sensitivity":[137],"hyper-parameter":[139],"selection":[140],"compared":[141],"with":[142],"Critic,":[146],"Automation,":[151],"algorithms.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}