{"id":"https://openalex.org/W3095881123","doi":"https://doi.org/10.1007/978-3-030-61616-8_25","title":"Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards","display_name":"Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095881123","doi":"https://doi.org/10.1007/978-3-030-61616-8_25","mag":"3095881123"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-61616-8_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"book-chapter","type_crossref":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03080925/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018273862","display_name":"Guillaume Matheron","orcid":"https://orcid.org/0000-0001-6530-8784"},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Matheron","raw_affiliation_strings":["ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)"],"affiliations":[{"raw_affiliation_string":"ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107304346","display_name":"Nicolas Perrin","orcid":"https://orcid.org/0000-0003-2358-2915"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Perrin","raw_affiliation_strings":["ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)"],"affiliations":[{"raw_affiliation_string":"ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042850624","display_name":"Olivier Sigaud","orcid":"https://orcid.org/0000-0002-8544-0229"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Sigaud","raw_affiliation_strings":["ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)"],"affiliations":[{"raw_affiliation_string":"ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"apc_paid":null,"fwci":1.79,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":13,"citation_normalized_percentile":{"value":0.897349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":89},"biblio":{"volume":null,"issue":null,"first_page":"308","last_page":"320"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995,"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":0.9995,"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":0.9782,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184062},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.74902844},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6178252},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5721465},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.55753875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49737528},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4803806},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.45447052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45134446},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41801164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19336596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12061098},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07261297},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-61616-8_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-03080925","pdf_url":"https://hal.science/hal-03080925/document","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1911.11679","pdf_url":"https://arxiv.org/pdf/1911.11679","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-03080925","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.1911.11679","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal.science/hal-03080925","pdf_url":"https://hal.science/hal-03080925/document","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.64,"display_name":"No poverty"}],"grants":[],"datasets":[],"versions":["https://openalex.org/W3095881123"],"referenced_works_count":15,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1980241579","https://openalex.org/W2121863487","https://openalex.org/W2125074935","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2785542505","https://openalex.org/W2904453761","https://openalex.org/W2924131335","https://openalex.org/W2962821147","https://openalex.org/W2963923407","https://openalex.org/W3097999317"],"related_works":["https://openalex.org/W4391331176","https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2586732548","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2024136090"],"abstract_inverted_index":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3095881123","counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2024-12-09T18:34:02.756425","created_date":"2020-11-09"}