{"id":"https://openalex.org/W4297740831","doi":"https://doi.org/10.48550/arxiv.1906.04452","title":"Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer","display_name":"Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer","publication_year":2019,"publication_date":"2019-06-11","ids":{"openalex":"https://openalex.org/W4297740831","doi":"https://doi.org/10.48550/arxiv.1906.04452"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-02285839v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-02285839v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML Workshop on \u201cMulti-Task and Lifelong Reinforcement Learning\u201d, Jun 2019, Long Beach, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.1906.04452","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Traor\u00e9, Ren\u00e9","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Traor\u00e9, Ren\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025408105","display_name":"Hugo Caselles-Dupr\u00e9","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caselles-Dupr\u00e9, Hugo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006026661","display_name":"Timoth\u00e9e Lesort","orcid":"https://orcid.org/0000-0002-8669-0764","observed_orcids":["https://orcid.org/0000-0002-8669-0764"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I201181511","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es","ror":"https://ror.org/0309cs235","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210140930","display_name":"Thales (France)","ror":"https://ror.org/04emwm605","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4405258625","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es Paris","ror":"https://ror.org/0106ccb15","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102","https://openalex.org/I4405258625"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lesort, Timoth\u00e9e","raw_affiliation_strings":["Flowers Laboratory (ENSTA ParisTech , INRIA)","Theresis Lab , Thales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flowers Laboratory (ENSTA ParisTech , INRIA)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I201181511","https://openalex.org/I4405258625"]},{"raw_affiliation_string":"Theresis Lab , Thales","institution_ids":["https://openalex.org/I4210140930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065902491","display_name":"Te Sun","orcid":"https://orcid.org/0009-0006-7840-4955","observed_orcids":["https://orcid.org/0009-0006-7840-4955"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I201181511","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es","ror":"https://ror.org/0309cs235","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4405258625","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es Paris","ror":"https://ror.org/0106ccb15","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102","https://openalex.org/I4405258625"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sun, Te","raw_affiliation_strings":["Flowers Laboratory (ENSTA ParisTech , INRIA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flowers Laboratory (ENSTA ParisTech , INRIA)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I201181511","https://openalex.org/I4405258625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058176171","display_name":"Natalia D\u00edaz-Rodr\u00edguez","orcid":"https://orcid.org/0000-0003-3362-9326","observed_orcids":["https://orcid.org/0000-0003-3362-9326"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D\u00edaz-Rodr\u00edguez, Natalia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027931470","display_name":"David Filliat","orcid":"https://orcid.org/0000-0002-5739-1618","observed_orcids":["https://orcid.org/0000-0002-5739-1618"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I201181511","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es","ror":"https://ror.org/0309cs235","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4405258625","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es Paris","ror":"https://ror.org/0106ccb15","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102","https://openalex.org/I4405258625"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Filliat, David","raw_affiliation_strings":["Flowers Laboratory (ENSTA ParisTech , INRIA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flowers Laboratory (ENSTA ParisTech , INRIA)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I201181511","https://openalex.org/I4405258625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3867,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.87061319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00019999999494757503,"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/T10653","display_name":"Robot Manipulation and Learning","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"}}],"keywords":[{"id":"https://openalex.org/keywords/continual-reinforcement-learning","display_name":"continual reinforcement learning","score":0.9229999780654907},{"id":"https://openalex.org/keywords/policy-distillation","display_name":"policy distillation","score":0.875},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.8679999709129333},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.6700000166893005},{"id":"https://openalex.org/keywords/omni-directional-robot","display_name":"omni-directional robot","score":0.8349999785423279},{"id":"https://openalex.org/keywords/state-representation-learning","display_name":"state representation learning","score":0.8429999947547913},{"id":"https://openalex.org/keywords/forgetting","display_name":"forgetting","score":0.3630000054836273},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.7720000147819519},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8847264051437378},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8311676979064941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491370439529419},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6677008271217346},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.639578640460968},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6082016229629517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5859734416007996},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4859417676925659},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47817927598953247},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4552057087421417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45011836290359497},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.41982588171958923},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1268461048603058},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-02285839v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-02285839v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML Workshop on \u201cMulti-Task and Lifelong Reinforcement Learning\u201d, Jun 2019, Long Beach, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1906.04452","doi":"https://doi.org/10.48550/arxiv.1906.04452","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.04452","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.1906.04452","doi":"https://doi.org/10.48550/arxiv.1906.04452","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.04452","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.4156000018119812}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2144823724","https://openalex.org/W2160178500","https://openalex.org/W2210483910","https://openalex.org/W2396961959","https://openalex.org/W2426267443","https://openalex.org/W2473930607","https://openalex.org/W2530944449","https://openalex.org/W2554863749","https://openalex.org/W2560647685","https://openalex.org/W2567455162","https://openalex.org/W2583761661","https://openalex.org/W2605102758","https://openalex.org/W2618767506","https://openalex.org/W2733961795","https://openalex.org/W2737492962","https://openalex.org/W2751258126","https://openalex.org/W2754695199","https://openalex.org/W2787666871","https://openalex.org/W2788781499","https://openalex.org/W2808844346","https://openalex.org/W2809425026","https://openalex.org/W2891707612","https://openalex.org/W2892673593","https://openalex.org/W2894485595","https://openalex.org/W2897007337","https://openalex.org/W2902907165","https://openalex.org/W2906272760","https://openalex.org/W2916592595","https://openalex.org/W2947638559","https://openalex.org/W2963156511","https://openalex.org/W2963167310","https://openalex.org/W2963199420","https://openalex.org/W2963430173","https://openalex.org/W2963577698","https://openalex.org/W2963850662","https://openalex.org/W2964001908","https://openalex.org/W2974990249","https://openalex.org/W7148977645"],"related_works":["https://openalex.org/W2962515681","https://openalex.org/W7204206643","https://openalex.org/W4401416949","https://openalex.org/W3183112146","https://openalex.org/W4405895629","https://openalex.org/W2096765839","https://openalex.org/W7221101955","https://openalex.org/W4364374595","https://openalex.org/W4403938968","https://openalex.org/W7054694002"],"abstract_inverted_index":{"We":[0,36],"focus":[1],"on":[2,40,47],"the":[3],"problem":[4],"of":[5,61],"teaching":[6],"a":[7,16,52,93],"robot":[8,21],"to":[9,25,44,88],"solve":[10,26],"tasks":[11,28,50],"presented":[12],"sequentially,":[13],"i.e.,":[14],"in":[15],"continual":[17],"learning":[18,64],"scenario.":[19],"The":[20],"should":[22],"be":[23],"able":[24],"all":[27,98],"it":[29],"has":[30],"encountered,":[31],"without":[32],"forgetting":[33],"past":[34],"tasks.":[35,100],"provide":[37],"preliminary":[38],"work":[39],"applying":[41],"Reinforcement":[42],"Learning":[43],"such":[45],"setting,":[46],"2D":[48],"navigation":[49],"for":[51],"3":[53],"wheel":[54],"omni-directional":[55],"robot.":[56],"Our":[57],"approach":[58],"takes":[59],"advantage":[60],"state":[62],"representation":[63],"and":[65],"policy":[66],"distillation.":[67],"Policies":[68],"are":[69],"trained":[70],"using":[71],"learned":[72],"features":[73],"as":[74],"input,":[75],"rather":[76],"than":[77],"raw":[78],"observations,":[79],"allowing":[80],"better":[81],"sample":[82],"efficiency.":[83],"Policy":[84],"distillation":[85],"is":[86],"used":[87],"combine":[89],"multiple":[90],"policies":[91],"into":[92],"single":[94],"one":[95],"that":[96],"solves":[97],"encountered":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-09-30T00:00:00"}