{"id":"https://openalex.org/W2951941324","doi":"https://doi.org/10.1109/icarcv.2018.8581309","title":"Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge","display_name":"Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2951941324","doi":"https://doi.org/10.1109/icarcv.2018.8581309","mag":"2951941324"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv.2018.8581309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2018.8581309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.02896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061214743","display_name":"Doo Re Song","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Doo Re Song","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019129514","display_name":"Chuanyu Yang","orcid":"https://orcid.org/0000-0001-9082-5193"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chuanyu Yang","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043683982","display_name":"Christopher McGreavy","orcid":"https://orcid.org/0000-0001-8424-1941"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher McGreavy","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351560","display_name":"Zhibin Li","orcid":"https://orcid.org/0000-0002-6357-7419"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhibin Li","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.1092,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93471896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10812","display_name":"Human Pose and Action Recognition","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/traverse","display_name":"Traverse","score":0.8929492235183716},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.8430819511413574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6630057096481323},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.6455488204956055},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.604985237121582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.550254762172699},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5396201014518738},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5055756568908691},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.4637618064880371},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.45394471287727356},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42990821599960327},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3266153335571289},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3263171315193176},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2307533323764801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19203826785087585},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15543517470359802}],"concepts":[{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.8929492235183716},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8430819511413574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6630057096481323},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.6455488204956055},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.604985237121582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550254762172699},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5396201014518738},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5055756568908691},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.4637618064880371},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.45394471287727356},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42990821599960327},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3266153335571289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3263171315193176},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2307533323764801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19203826785087585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15543517470359802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icarcv.2018.8581309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2018.8581309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.02896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.02896","pdf_url":"https://arxiv.org/pdf/1710.02896","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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/93d5950f-a2c8-4f03-9cb2-4c93dd1a8aba","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/93d5950f-a2c8-4f03-9cb2-4c93dd1a8aba","pdf_url":"https://www.research.ed.ac.uk/files/76210380/Recurrent_deterministic_policy_gradient_method_for_bipeda_locomotion_on_rough_terrain_challenge.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Re Song, D, Yang, C, McGreavy, C & Li, Z 2018, Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge. in Proceedings of the 15th International Conference on Control, Automation, Robotics and Vision (ICARCV 2018). Institute of Electrical and Electronics Engineers, Singapore, Singapore, pp. 311-318, 15th International Conference on Control, Automation, Robotics and Vision, Singapore, 18/11/18. https://doi.org/10.1109/ICARCV.2018.8581309","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/93d5950f-a2c8-4f03-9cb2-4c93dd1a8aba","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/93d5950f-a2c8-4f03-9cb2-4c93dd1a8aba","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.02896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.02896","pdf_url":"https://arxiv.org/pdf/1710.02896","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":[{"id":"https://openalex.org/G2838024195","display_name":"UK Robotics and Artificial Intelligence Hub for Offshore Energy Asset Integrity Management","funder_award_id":"EP/R026173/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4483049737","display_name":null,"funder_award_id":"EP/R026173/1","funder_id":"https://openalex.org/F4320334245","funder_display_name":"Offshore Robotics for Certification of Assets"},{"id":"https://openalex.org/G5187574974","display_name":null,"funder_award_id":"1957059","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8602921712","display_name":null,"funder_award_id":"EP/R026173","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334245","display_name":"Offshore Robotics for Certification of Assets","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1011330699","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2014505645","https://openalex.org/W2034725503","https://openalex.org/W2064675550","https://openalex.org/W2098523767","https://openalex.org/W2100677568","https://openalex.org/W2103581399","https://openalex.org/W2109008048","https://openalex.org/W2121092017","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2290104316","https://openalex.org/W2291973609","https://openalex.org/W2342662072","https://openalex.org/W2522489477","https://openalex.org/W2580175322","https://openalex.org/W2608117728","https://openalex.org/W2623491082","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2772721022","https://openalex.org/W2784192398","https://openalex.org/W2950178297","https://openalex.org/W2950872548","https://openalex.org/W2962747693","https://openalex.org/W2962938178","https://openalex.org/W2963024489","https://openalex.org/W2963590100","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2963889160","https://openalex.org/W2964043796","https://openalex.org/W3041202696","https://openalex.org/W3101808543","https://openalex.org/W4214717370","https://openalex.org/W4254755460","https://openalex.org/W4293775712","https://openalex.org/W4302570325","https://openalex.org/W4394662669","https://openalex.org/W6636732284","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6696380822","https://openalex.org/W6704571135","https://openalex.org/W6727252785","https://openalex.org/W6739193204"],"related_works":["https://openalex.org/W2377402383","https://openalex.org/W2046459260","https://openalex.org/W2380835401","https://openalex.org/W2381912691","https://openalex.org/W2350381577","https://openalex.org/W2353618196","https://openalex.org/W2348074676","https://openalex.org/W4200195314","https://openalex.org/W4389574494","https://openalex.org/W2156329176"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,125],"deep":[4],"learning":[5,58,87],"framework":[6,88],"that":[7,112],"is":[8,106],"capable":[9],"of":[10,21,31,43,62,66,73,78,127],"solving":[11],"partially":[12],"observable":[13],"locomotion":[14],"tasks":[15],"based":[16,57],"on":[17,29],"our":[18,55],"novel":[19],"interpretation":[20],"Recurrent":[22],"Deterministic":[23],"Policy":[24],"Gradient":[25],"(RDPG).":[26],"We":[27],"study":[28,110],"bias":[30],"sampled":[32],"error":[33],"measure":[34],"and":[35,45,76,129],"its":[36],"variance":[37],"induced":[38],"by":[39,82,117],"the":[40,93,113,118,131],"partial":[41,103],"observability":[42],"environment":[44,100],"subtrajectory":[46],"sampling,":[47],"respectively.":[48],"Three":[49],"major":[50],"improvements":[51],"are":[52,121],"introduced":[53],"in":[54,96],"RDPG":[56,119],"framework:":[59],"tail-step":[60],"bootstrap":[61],"temporal":[63,74],"difference,":[64],"initialisation":[65],"hidden":[67],"state":[68,104],"using":[69],"past":[70],"subtrajectory,":[71],"truncation":[72],"backpropagation,":[75],"injection":[77],"external":[79],"experiences":[80],"learned":[81],"other":[83],"agents.":[84],"The":[85],"proposed":[86],"was":[89],"implemented":[90],"to":[91,124,133],"solve":[92],"Bipedal-Walker":[94],"challenge":[95],"OpenAI's":[97],"gym":[98],"simulation":[99,109],"where":[101],"only":[102],"information":[105],"available.":[107],"Our":[108],"shows":[111],"autonomous":[114],"behaviors":[115],"generated":[116],"agent":[120,132],"highly":[122],"adaptive":[123],"variety":[126],"obstacles":[128],"enables":[130],"effectively":[134],"traverse":[135],"rugged":[136],"terrains":[137],"for":[138],"long":[139],"distance":[140],"with":[141],"higher":[142],"success":[143],"rate":[144],"than":[145],"leading":[146],"contenders.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-06-27T00:00:00"}