{"id":"https://openalex.org/W2903866873","doi":"https://doi.org/10.1007/s10994-019-05788-0","title":"TD-regularized actor-critic methods","display_name":"TD-regularized actor-critic methods","publication_year":2019,"publication_date":"2019-02-21","ids":{"openalex":"https://openalex.org/W2903866873","doi":"https://doi.org/10.1007/s10994-019-05788-0","mag":"2903866873"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05788-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05788-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05788-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05788-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Simone Parisi","orcid":"https://orcid.org/0000-0003-3886-8131"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]},{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simone Parisi","raw_affiliation_strings":["Technische Unviersitt Darmstadt, Hochschulstrasse 10, 64289 Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3886-8131","affiliations":[{"raw_affiliation_string":"Technische Unviersitt Darmstadt, Hochschulstrasse 10, 64289 Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I107257983"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Voot Tangkaratt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Voot Tangkaratt","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi Chuo-ku, Tokyo 103-0027, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi Chuo-ku, Tokyo 103-0027, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jan Peters","orcid":null},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]},{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Max-Planck-Institut fr Intelligente Systeme, Speemannstrasse 38, 72076 Tbingen, Germany","Technische Unviersitt Darmstadt, Hochschulstrasse 10, 64289 Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut fr Intelligente Systeme, Speemannstrasse 38, 72076 Tbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Technische Unviersitt Darmstadt, Hochschulstrasse 10, 64289 Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I107257983"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mohammad Emtiyaz Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mohammad Emtiyaz Khan","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi Chuo-ku, Tokyo 103-0027, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi Chuo-ku, Tokyo 103-0027, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107257983","https://openalex.org/I31512782"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.1674,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.90410654,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"108","issue":"8-9","first_page":"1467","last_page":"1501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8853999972343445,"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":0.8853999972343445,"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":0.016899999231100082,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.010599999688565731,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7159000039100647},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.7056000232696533},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.3734999895095825},{"id":"https://openalex.org/keywords/probably-approximately-correct-learning","display_name":"Probably approximately correct learning","score":0.2393999993801117}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7159000039100647},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.7056000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985999703407288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2393999993801117},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2295999974012375},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2207999974489212}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-019-05788-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05788-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05788-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1812.08288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.08288","pdf_url":"https://arxiv.org/pdf/1812.08288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05788-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05788-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05788-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903866873.pdf","grobid_xml":"https://content.openalex.org/works/W2903866873.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1499669280","https://openalex.org/W1646707810","https://openalex.org/W2108682071","https://openalex.org/W2119717200","https://openalex.org/W2136064843","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2162849300","https://openalex.org/W2167144895","https://openalex.org/W2172968643","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2259167532","https://openalex.org/W2260756217","https://openalex.org/W2411690432","https://openalex.org/W2473408367","https://openalex.org/W2593658277","https://openalex.org/W2727576081","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2786303200","https://openalex.org/W2787613197","https://openalex.org/W2787938642","https://openalex.org/W4237284205","https://openalex.org/W4241521318","https://openalex.org/W4248446246","https://openalex.org/W4250589301","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6653548176","https://openalex.org/W6677916085","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6696324988","https://openalex.org/W6737893269","https://openalex.org/W6744123322","https://openalex.org/W6746636705"],"related_works":[],"abstract_inverted_index":{"Actor-critic":[0],"methods":[1],"can":[2],"achieve":[3],"incredible":[4],"performance":[5,111],"on":[6,117],"difficult":[7],"reinforcement":[8],"learning":[9,59],"problems,":[10],"but":[11],"they":[12],"are":[13],"also":[14],"prone":[15],"to":[16,22,56,106],"instability.":[17],"This":[18,74],"is":[19,88,101],"partly":[20],"due":[21],"the":[23,26,44,48,58,62,66,72,82,86,97,113],"interaction":[24],"between":[25],"actor":[27,63,83],"and":[28,46,109],"critic":[29,87],"during":[30],"learning,":[31],"e.g.,":[32],"an":[33],"inaccurate":[34],"step":[35],"taken":[36],"by":[37,64,77],"one":[38],"of":[39,61,71,112],"them":[40],"might":[41],"adversely":[42],"affect":[43],"other":[45],"destabilize":[47],"learning.":[49],"To":[50],"avoid":[51],"such":[52],"issues,":[53],"we":[54,95],"propose":[55],"regularize":[57],"objective":[60],"penalizing":[65],"temporal":[67],"difference":[68],"(TD)":[69],"error":[70],"critic.":[73],"improves":[75],"stability":[76,108],"avoiding":[78],"large":[79],"steps":[80],"in":[81],"update":[84],"whenever":[85],"highly":[89],"inaccurate.":[90],"The":[91],"resulting":[92],"method,":[93,100],"which":[94],"call":[96],"TD-regularized":[98],"actor-critic":[99,114],"a":[102],"simple":[103],"plug-and-play":[104],"approach":[105],"improve":[107],"overall":[110],"methods.":[115],"Evaluations":[116],"standard":[118],"benchmarks":[119],"confirm":[120],"this.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-12-22T00:00:00"}