{"id":"https://openalex.org/W3203023912","doi":"https://doi.org/10.48550/arxiv.2109.13338","title":"Solving Challenging Control Problems Using Two-Staged Deep Reinforcement Learning","display_name":"Solving Challenging Control Problems Using Two-Staged Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3203023912","doi":"https://doi.org/10.48550/arxiv.2109.13338","mag":"3203023912"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2109.13338","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.13338","pdf_url":"https://arxiv.org/pdf/2109.13338","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.13338","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002989902","display_name":"Nitish Sontakke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sontakke, Nitish","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064581452","display_name":"Sehoon Ha","orcid":"https://orcid.org/0000-0002-1972-328X","observed_orcids":["https://orcid.org/0000-0002-1972-328X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ha, Sehoon","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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"}},{"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8420000076293945},{"id":"https://openalex.org/keywords/two-stage-learning","display_name":"two-stage learning","score":0.765999972820282},{"id":"https://openalex.org/keywords/motion-planning","display_name":"motion planning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/motion-imitation","display_name":"motion imitation","score":0.9390000104904175},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.7099999785423279},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.7889999747276306},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.45899999141693115},{"id":"https://openalex.org/keywords/quadrupedal-locomotion","display_name":"quadrupedal locomotion","score":0.8870000243186951},{"id":"https://openalex.org/keywords/probabilistic-roadmaps","display_name":"probabilistic roadmaps","score":0.609000027179718},{"id":"https://openalex.org/keywords/high-dimensional-control","display_name":"high-dimensional control","score":0.5249999761581421}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8401762247085571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515050172805786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.681699275970459},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.592472493648529},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5875074863433838},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5610551238059998},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5408798456192017},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5072779059410095},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.501173734664917},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.48391610383987427},{"id":"https://openalex.org/C187878255","wikidata":"https://www.wikidata.org/wiki/Q2037215","display_name":"Rocket (weapon)","level":2,"score":0.4629752039909363},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.43230491876602173},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.24706178903579712},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12333890795707703},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2109.13338","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.13338","pdf_url":"https://arxiv.org/pdf/2109.13338","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2109.13338","doi":"https://doi.org/10.48550/arxiv.2109.13338","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.13338","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.13338","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.13338","pdf_url":"https://arxiv.org/pdf/2109.13338","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7400000095367432}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2028208724","https://openalex.org/W2099893201","https://openalex.org/W2101207292","https://openalex.org/W2139053308","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2766447205","https://openalex.org/W2784947652","https://openalex.org/W2788200022","https://openalex.org/W2796290181","https://openalex.org/W2899496413","https://openalex.org/W2907537824","https://openalex.org/W2911087563","https://openalex.org/W2947525798","https://openalex.org/W2951805468","https://openalex.org/W2954829582","https://openalex.org/W2963184939","https://openalex.org/W2974120010","https://openalex.org/W3003817470","https://openalex.org/W3007553593","https://openalex.org/W3014488508","https://openalex.org/W3021055704","https://openalex.org/W3069663381","https://openalex.org/W3095484646","https://openalex.org/W3104876774","https://openalex.org/W3105372678","https://openalex.org/W3108883557","https://openalex.org/W3115511323","https://openalex.org/W3130987264","https://openalex.org/W3185291728","https://openalex.org/W4253729359","https://openalex.org/W4311443585"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"We":[0,140],"present":[1],"a":[2,83,102,123],"deep":[3,68,94,162],"reinforcement":[4],"learning":[5],"(deep":[6],"RL)":[7],"algorithm":[8],"that":[9,61,105,142],"consists":[10],"of":[11,93],"learning-based":[12],"motion":[13,71,74,77,85,98,110],"planning":[14,72,78,91],"and":[15,73,115,152],"imitation":[16,99],"to":[17,81,127,136],"tackle":[18],"challenging":[19,41,147],"control":[20,34,103,148],"problems.":[21],"Deep":[22],"RL":[23,69,163],"has":[24],"been":[25],"an":[26,59],"effective":[27],"tool":[28],"for":[29],"solving":[30],"many":[31],"high-dimensional":[32],"continuous":[33],"problems,":[35,149],"but":[36],"it":[37],"cannot":[38,156],"effectively":[39],"solve":[40,146],"problems":[42],"with":[43,112,168],"certain":[44],"properties,":[45],"such":[46],"as":[47],"sparse":[48],"reward":[49],"functions":[50],"or":[51,165],"sensitive":[52],"dynamics.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"propose":[58],"approach":[60,144],"decomposes":[62],"the":[63,89,97,108,128,137,160,166],"given":[64,109],"problem":[65],"into":[66],"two":[67],"stages:":[70],"imitation.":[75],"The":[76],"stage":[79,100],"seeks":[80],"compute":[82],"feasible":[84],"plan":[86,111],"by":[87,159],"leveraging":[88],"powerful":[90],"capability":[92],"RL.":[95],"Subsequently,":[96],"learns":[101],"policy":[104],"can":[106,145],"imitate":[107],"realistic":[113],"sensors":[114],"actuation":[116],"models.":[117],"This":[118],"new":[119],"formulation":[120,164],"requires":[121],"only":[122],"nominal":[124],"added":[125],"cost":[126],"user":[129],"because":[130],"both":[131],"stages":[132],"require":[133],"minimal":[134],"changes":[135],"original":[138],"problem.":[139],"demonstrate":[141],"our":[143],"rocket":[150],"navigation,":[151],"quadrupedal":[153],"locomotion,":[154],"which":[155],"be":[157],"solved":[158],"monolithic":[161],"version":[167],"Probabilistic":[169],"Roadmap.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-10-11T00:00:00"}