{"id":"https://openalex.org/W2995636097","doi":null,"title":"Option Discovery using Deep Skill Chaining","display_name":"Option Discovery using Deep Skill Chaining","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995636097","mag":"2995636097"},"language":"en","primary_location":{"id":"mag:2995636097","doi":null,"is_oa":false,"landing_page_url":"https://www.openreview.net/pdf?id=B1gqipNYwH","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5080105613","display_name":"Akhil Bagaria","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akhil Bagaria","raw_affiliation_strings":["Brown University, Providence, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, United States","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078124517","display_name":"George Konidaris","orcid":"https://orcid.org/0000-0002-4460-2519","observed_orcids":["https://orcid.org/0000-0002-4460-2519"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Konidaris","raw_affiliation_strings":["Brown University, Providence, United States"],"raw_orcid":"https://orcid.org/0000-0002-4460-2519","affiliations":[{"raw_affiliation_string":"Brown University, Providence, United States","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":3.4391,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.94239764,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"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":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/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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/skill-discovery","display_name":"skill discovery","score":0.7749999761581421},{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.8709999918937683},{"id":"https://openalex.org/keywords/temporally-extended-actions","display_name":"temporally extended actions","score":0.8119999766349792},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.8119999766349792},{"id":"https://openalex.org/keywords/high-dimensional-control","display_name":"high-dimensional control","score":0.5609999895095825}],"concepts":[{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.9785050749778748},{"id":"https://openalex.org/C142614401","wikidata":"https://www.wikidata.org/wiki/Q777433","display_name":"Forward chaining","level":3,"score":0.800152063369751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778537392616272},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.761813759803772},{"id":"https://openalex.org/C129916263","wikidata":"https://www.wikidata.org/wiki/Q1141183","display_name":"Backward chaining","level":4,"score":0.6789325475692749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6512556672096252},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5242027044296265},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48098504543304443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43605583906173706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42165088653564453},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.15234512090682983},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.13544508814811707},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.05837583541870117},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995636097","doi":null,"is_oa":false,"landing_page_url":"https://www.openreview.net/pdf?id=B1gqipNYwH","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W17007763","https://openalex.org/W58569852","https://openalex.org/W198337890","https://openalex.org/W567721252","https://openalex.org/W1494114146","https://openalex.org/W1503821144","https://openalex.org/W1586944634","https://openalex.org/W1592847719","https://openalex.org/W1595483645","https://openalex.org/W1678414046","https://openalex.org/W1963873191","https://openalex.org/W1968768508","https://openalex.org/W2041367235","https://openalex.org/W2090170171","https://openalex.org/W2101234009","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2124684839","https://openalex.org/W2130535800","https://openalex.org/W2132622533","https://openalex.org/W2145339207","https://openalex.org/W2153947321","https://openalex.org/W2158782408","https://openalex.org/W2160371091","https://openalex.org/W2173248099","https://openalex.org/W2217025414","https://openalex.org/W2257275784","https://openalex.org/W2296356821","https://openalex.org/W2561776174","https://openalex.org/W2594829461","https://openalex.org/W2737215407","https://openalex.org/W2765308067","https://openalex.org/W2771734675","https://openalex.org/W2774718932","https://openalex.org/W2785940258","https://openalex.org/W2787066086","https://openalex.org/W2803281228","https://openalex.org/W2804672169","https://openalex.org/W2884439071","https://openalex.org/W2891540084","https://openalex.org/W2899289853","https://openalex.org/W2918355317","https://openalex.org/W2926786214","https://openalex.org/W2949604932","https://openalex.org/W2954142106","https://openalex.org/W2963011537","https://openalex.org/W2963142324","https://openalex.org/W2963276097","https://openalex.org/W2963560777","https://openalex.org/W2963641140","https://openalex.org/W2964001908","https://openalex.org/W2964067469","https://openalex.org/W2964227312","https://openalex.org/W2970163238","https://openalex.org/W2995363872"],"related_works":["https://openalex.org/W2108535023","https://openalex.org/W4404035314","https://openalex.org/W7097166093","https://openalex.org/W4415796807","https://openalex.org/W2132112091","https://openalex.org/W6945719594","https://openalex.org/W4392222433","https://openalex.org/W4285077612","https://openalex.org/W7133266254","https://openalex.org/W7033920574"],"abstract_inverted_index":{"Autonomously":[0],"discovering":[1],"temporally":[2],"extended":[3],"actions,":[4],"or":[5],"skills,":[6],"is":[7],"a":[8,17],"longstanding":[9],"goal":[10],"of":[11],"hierarchical":[12],"reinforcement":[13],"learning.":[14],"We":[15,56],"propose":[16],"new":[18],"algorithm":[19],"that":[20,47,58],"combines":[21],"skill":[22,40,60,70],"chaining":[23,61],"with":[24,44],"deep":[25,39,59],"neural":[26],"networks":[27],"to":[28,53],"autonomously":[29],"discover":[30],"skills":[31,43],"in":[32,73],"high-dimensional,":[33],"continuous":[34,75],"domains.":[35],"The":[36],"resulting":[37],"algorithm,":[38],"chaining,":[41],"constructs":[42],"the":[45,51],"property":[46],"executing":[48],"one":[49],"enables":[50],"agent":[52],"execute":[54],"another.":[55],"demonstrate":[57],"significantly":[62],"outperforms":[63],"both":[64],"non-hierarchical":[65],"agents":[66],"and":[67],"other":[68],"state-of-the-art":[69],"discovery":[71],"techniques":[72],"challenging":[74],"control":[76],"tasks.":[77]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2019-12-26T00:00:00"}