{"id":"https://openalex.org/W3091126461","doi":"https://doi.org/10.1109/icra40945.2020.9197052","title":"Evaluating Adaptation Performance of Hierarchical Deep Reinforcement Learning","display_name":"Evaluating Adaptation Performance of Hierarchical Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3091126461","doi":"https://doi.org/10.1109/icra40945.2020.9197052","mag":"3091126461"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5032797879","display_name":"Neale Van Stolen","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neale Van Stolen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454633","display_name":"Seung Hyun Kim","orcid":"https://orcid.org/0000-0003-1052-8944"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung Hyun Kim","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041059272","display_name":"Huy Tran","orcid":"https://orcid.org/0000-0001-6261-6167"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huy T. Tran","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073739058","display_name":"Girish Chowdhary","orcid":"https://orcid.org/0000-0002-4657-307X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Girish Chowdhary","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032797879"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11993884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"11457","last_page":"11463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.982699990272522,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9815000295639038,"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":0.9304163455963135},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.8254657983779907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7861524820327759},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6103572845458984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5535512566566467},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.541195273399353},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5408215522766113},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.511461615562439},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5113427042961121},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4384625554084778},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09923359751701355}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9304163455963135},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.8254657983779907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861524820327759},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6103572845458984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5535512566566467},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.541195273399353},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5408215522766113},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.511461615562439},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5113427042961121},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4384625554084778},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09923359751701355},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W256201028","https://openalex.org/W1191599655","https://openalex.org/W1492974543","https://openalex.org/W1771410628","https://openalex.org/W1801398035","https://openalex.org/W1848094219","https://openalex.org/W1977548549","https://openalex.org/W2021128738","https://openalex.org/W2078009415","https://openalex.org/W2109910161","https://openalex.org/W2117359296","https://openalex.org/W2162022118","https://openalex.org/W2298457129","https://openalex.org/W2472819217","https://openalex.org/W2534269850","https://openalex.org/W2592798481","https://openalex.org/W2739330054","https://openalex.org/W2753160622","https://openalex.org/W2783250069","https://openalex.org/W2810602713","https://openalex.org/W2949247522","https://openalex.org/W2952629144","https://openalex.org/W2962817122","https://openalex.org/W2962821147","https://openalex.org/W2963262099","https://openalex.org/W2963341924","https://openalex.org/W2964227312","https://openalex.org/W2989068617","https://openalex.org/W3099518626","https://openalex.org/W6627932998","https://openalex.org/W6629554404","https://openalex.org/W6638018090","https://openalex.org/W6638853687","https://openalex.org/W6697459119","https://openalex.org/W6703271639","https://openalex.org/W6717697761","https://openalex.org/W6720057410","https://openalex.org/W6727349600","https://openalex.org/W6728925229","https://openalex.org/W6734678876","https://openalex.org/W6743661861","https://openalex.org/W6756287877"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1,28],"Learning":[2],"has":[3,11],"been":[4],"used":[5],"to":[6,16,54,91],"exploit":[7],"specific":[8],"environments,":[9],"but":[10],"difficulty":[12],"transferring":[13],"learned":[14],"policies":[15],"new":[17,85],"situations.":[18],"This":[19],"issue":[20],"poses":[21],"a":[22,51,63,84],"problem":[23],"for":[24,68],"practical":[25],"applications":[26],"of":[27,46],"Learning,":[29],"as":[30],"real-world":[31],"scenarios":[32],"may":[33],"introduce":[34,62],"unexpected":[35],"differences":[36],"that":[37],"drastically":[38],"reduce":[39],"policy":[40],"performance.":[41],"We":[42,60,79],"propose":[43],"the":[44,69,87],"use":[45],"differentiated":[47],"sub-policies":[48],"governed":[49],"by":[50],"hierarchical":[52,70],"controller":[53,71],"support":[55],"adaptation":[56,93],"in":[57,83,94],"such":[58],"scenarios.":[59],"also":[61],"confidence-":[64],"based":[65],"training":[66,74],"process":[67],"which":[72],"improves":[73],"stability":[75],"and":[76],"convergence":[77],"times.":[78],"evaluate":[80],"these":[81],"methods":[82],"Capture":[86],"Flag":[88],"environment":[89],"designed":[90],"explore":[92],"autonomous":[95],"multi-agent":[96],"settings.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}