{"id":"https://openalex.org/W3042938692","doi":null,"title":"Learning Intrinsically Motivated Options to Stimulate Policy Exploration","display_name":"Learning Intrinsically Motivated Options to Stimulate Policy Exploration","publication_year":2020,"publication_date":"2020-06-12","ids":{"openalex":"https://openalex.org/W3042938692","mag":"3042938692"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-05688566v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05688566v1","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"4th Lifelong Machine Learning Workshop at ICML 2020, Jul 2020, Onlince Conference, Austria","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05688566v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057955697","display_name":"Louis Bagot","orcid":"https://orcid.org/0000-0001-6300-6993","observed_orcids":["https://orcid.org/0000-0001-6300-6993"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis Bagot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084961388","display_name":"Kevin Mets","orcid":"https://orcid.org/0000-0002-4812-4841","observed_orcids":["https://orcid.org/0000-0002-4812-4841"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Mets","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4812-4841","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049021976","display_name":"Steven Latr\u00e9","orcid":"https://orcid.org/0000-0003-0351-1714","observed_orcids":["https://orcid.org/0000-0003-0351-1714"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Latr\u00e9","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0351-1714","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2388,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.4630955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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":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/T11574","display_name":"Artificial Intelligence in Games","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"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","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/intrinsic-motivation","display_name":"intrinsic motivation","score":0.7179999947547913},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.5370000004768372},{"id":"https://openalex.org/keywords/policy-exploration","display_name":"policy exploration","score":0.6039999723434448},{"id":"https://openalex.org/keywords/temporally-extended-actions","display_name":"temporally extended actions","score":0.7279999852180481},{"id":"https://openalex.org/keywords/task-transfer","display_name":"task transfer","score":0.6150000095367432},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5759999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.382373183965683}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-05688566v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05688566v1","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"4th Lifelong Machine Learning Workshop at ICML 2020, Jul 2020, Onlince Conference, Austria","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3042938692","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=Vcf1fDmBYJk","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05688566v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05688566v1","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"4th Lifelong Machine Learning Workshop at ICML 2020, Jul 2020, Onlince Conference, Austria","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2000514530","https://openalex.org/W2034806191","https://openalex.org/W2056354534","https://openalex.org/W2109910161","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2132622533","https://openalex.org/W2145339207","https://openalex.org/W2338197808","https://openalex.org/W2417786368","https://openalex.org/W2523728418","https://openalex.org/W2551887912","https://openalex.org/W2567015638","https://openalex.org/W2592915494","https://openalex.org/W2596982695","https://openalex.org/W2605102581","https://openalex.org/W2614839826","https://openalex.org/W2663108269","https://openalex.org/W2724169821","https://openalex.org/W2781726626","https://openalex.org/W2788741142","https://openalex.org/W2885550588","https://openalex.org/W2899205164","https://openalex.org/W2913343212","https://openalex.org/W2950040888","https://openalex.org/W2963276097"],"related_works":["https://openalex.org/W3015173317","https://openalex.org/W7133193794","https://openalex.org/W7100836732","https://openalex.org/W7048160779","https://openalex.org/W3204272549","https://openalex.org/W3193962195","https://openalex.org/W6943781246","https://openalex.org/W3184308941","https://openalex.org/W1999643445","https://openalex.org/W7169674028"],"abstract_inverted_index":{"A":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"agent":[4],"needs":[5],"to":[6,15,27,36,46,54,67,75,102],"find":[7],"an":[8,76],"optimal":[9],"sequence":[10],"of":[11,22,92,95],"actions":[12,66],"in":[13],"order":[14],"maximize":[16],"rewards.":[17],"This":[18],"requires":[19],"consistent":[20],"exploration":[21,38,61],"states":[23],"and":[24,100],"action":[25],"sequences":[26],"ensure":[28],"the":[29,89],"policy":[30],"found":[31],"is":[32,39],"optimal.":[33],"One":[34],"way":[35],"motivate":[37],"through":[40,60],"intrinsic":[41,58,77],"rewards,":[42,96],"i.e.":[43,63],"agent-induced":[44],"rewards":[45,59],"guide":[47],"itself":[48],"towards":[49],"interesting":[50],"behaviors.":[51],"We":[52,79],"propose":[53],"learn":[55],"from":[56],"such":[57],"options,":[62],"additional":[64],"temporally-extended":[65],"call":[68],"separate":[69],"policies":[70],"(or":[71],"\"Explorer\"":[72],"agents)":[73],"associated":[74],"reward.":[78],"show":[80],"that":[81],"this":[82],"method":[83,91],"has":[84],"several":[85],"key":[86],"advantages":[87],"over":[88],"usual":[90],"weighted":[93],"sum":[94],"mainly":[97],"task-transfer":[98],"abilities":[99],"scalability":[101],"multiple":[103],"reward":[104],"functions.":[105]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2020-07-23T00:00:00"}