{"id":"https://openalex.org/W3092277419","doi":"https://doi.org/10.1145/3424636.3426907","title":"Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning","display_name":"Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-16","ids":{"openalex":"https://openalex.org/W3092277419","doi":"https://doi.org/10.1145/3424636.3426907","mag":"3092277419"},"language":"en","primary_location":{"id":"doi:10.1145/3424636.3426907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3424636.3426907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Motion, Interaction and Games","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.04304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053770584","display_name":"Daniele Reda","orcid":"https://orcid.org/0000-0002-7101-0519"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Daniele Reda","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000510646","display_name":"Tianxin Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tianxin Tao","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052748246","display_name":"Michiel van de Panne","orcid":"https://orcid.org/0000-0002-9123-3672"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michiel van de Panne","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053770584"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":4.1544,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94456276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9948999881744385,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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":0.8622503280639648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6920604109764099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6154411435127258},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5969825387001038},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5518685579299927},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5414772629737854},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.5392261147499084},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49939846992492676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40540850162506104},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3780522346496582}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8622503280639648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920604109764099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154411435127258},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5969825387001038},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5518685579299927},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5414772629737854},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.5392261147499084},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49939846992492676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40540850162506104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3780522346496582},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3424636.3426907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3424636.3426907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Motion, Interaction and Games","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.04304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.04304","pdf_url":"https://arxiv.org/pdf/2010.04304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.04304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.04304","pdf_url":"https://arxiv.org/pdf/2010.04304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1564670092","https://openalex.org/W2005478758","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2296073425","https://openalex.org/W2546975091","https://openalex.org/W2605102581","https://openalex.org/W2611706523","https://openalex.org/W2736601468","https://openalex.org/W2737215407","https://openalex.org/W2739330054","https://openalex.org/W2784449021","https://openalex.org/W2787938642","https://openalex.org/W2789525339","https://openalex.org/W2796290181","https://openalex.org/W2801567109","https://openalex.org/W2809668646","https://openalex.org/W2898436992","https://openalex.org/W2899718839","https://openalex.org/W2902334345","https://openalex.org/W2913403708","https://openalex.org/W2962749646","https://openalex.org/W2963120839","https://openalex.org/W2963133245","https://openalex.org/W2963193690","https://openalex.org/W2981479926","https://openalex.org/W2984579799","https://openalex.org/W2989100706","https://openalex.org/W2995894173","https://openalex.org/W3006010246","https://openalex.org/W3012544020","https://openalex.org/W3029641972","https://openalex.org/W3035700320","https://openalex.org/W3090153548","https://openalex.org/W3104515094","https://openalex.org/W3105609823","https://openalex.org/W3108412994","https://openalex.org/W3150845012","https://openalex.org/W4300892751"],"related_works":["https://openalex.org/W1487956045","https://openalex.org/W1601503673","https://openalex.org/W1592154258","https://openalex.org/W1527882169","https://openalex.org/W1596535966","https://openalex.org/W4388039923","https://openalex.org/W2096246921","https://openalex.org/W2145935766","https://openalex.org/W2136562935","https://openalex.org/W26087330"],"abstract_inverted_index":{"Learning":[0],"to":[1,27,46,81,94,118,135,141,146],"locomote":[2],"is":[3,21,51],"one":[4],"of":[5,24,56,85,131,139],"the":[6,22,25,33,37,54,60,82,109,113,129],"most":[7],"common":[8],"tasks":[9],"in":[10,72,125],"physics-based":[11],"animation":[12],"and":[13,36,75,112],"deep":[14],"reinforcement":[15],"learning":[16,145],"(RL).":[17],"A":[18],"learned":[19],"policy":[20],"product":[23],"problem":[26],"be":[28],"solved,":[29],"as":[30,144],"embodied":[31],"by":[32],"RL":[34,38,47,61,87,132],"environment,":[35],"algorithm.":[39],"While":[40],"enormous":[41],"attention":[42],"has":[43],"been":[44],"devoted":[45],"algorithms,":[48],"much":[49],"less":[50],"known":[52],"about":[53],"impact":[55,128],"design":[57,70],"choices":[58,92],"for":[59],"environment.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,90],"show":[67],"that":[68],"environment":[69],"matters":[71],"significant":[73],"ways":[74],"document":[76],"how":[77],"it":[78],"can":[79],"contribute":[80],"brittle":[83],"nature":[84],"many":[86],"results.":[88],"Specifically,":[89],"examine":[91],"related":[93],"state":[95,98],"representations,":[96],"initial":[97],"distributions,":[99],"reward":[100],"structure,":[101],"control":[102,137],"frequency,":[103],"episode":[104],"termination":[105],"procedures,":[106],"curriculum":[107],"usage,":[108],"action":[110],"space,":[111],"torque":[114],"limits.":[115],"We":[116],"aim":[117],"stimulate":[119],"discussion":[120],"around":[121],"such":[122,143],"choices,":[123],"which":[124],"practice":[126],"strongly":[127],"success":[130],"when":[133],"applied":[134],"continuous-action":[136],"problems":[138],"interest":[140],"animation,":[142],"locomote.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-10-15T00:00:00"}