{"id":"https://openalex.org/W4313562908","doi":"https://doi.org/10.1109/humanoids53995.2022.10000068","title":"Improving Sample Efficiency of Example-Guided Deep Reinforcement Learning for Bipedal Walking","display_name":"Improving Sample Efficiency of Example-Guided Deep Reinforcement Learning for Bipedal Walking","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W4313562908","doi":"https://doi.org/10.1109/humanoids53995.2022.10000068"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids53995.2022.10000068","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/humanoids53995.2022.10000068","pdf_url":null,"source":{"id":"https://openalex.org/S4363608580","display_name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033635074","display_name":"Rustam Galljamov","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210095579","display_name":"Institute for Sports Medicine","ror":"https://ror.org/0084rd854","country_code":"DE","type":"other","lineage":["https://openalex.org/I4210095579"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rustam Galljamov","raw_affiliation_strings":["Intelligent Autonomous Systems Lab,Department of Computer Science,TU Darmstadt,Germany","Lauflabor Locomotion Laboratory, Institute of Sport Science, TU Darmstadt, Germany","Department of Computer Science, Intelligent Autonomous Systems Lab, TU Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Lab,Department of Computer Science,TU Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Lauflabor Locomotion Laboratory, Institute of Sport Science, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210095579"]},{"raw_affiliation_string":"Department of Computer Science, Intelligent Autonomous Systems Lab, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048970503","display_name":"Guoping Zhao","orcid":"https://orcid.org/0000-0002-1908-5388"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210095579","display_name":"Institute for Sports Medicine","ror":"https://ror.org/0084rd854","country_code":"DE","type":"other","lineage":["https://openalex.org/I4210095579"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guoping Zhao","raw_affiliation_strings":["Institute of Sport Science,Lauflabor Locomotion Laboratory,TU Darmstadt,Germany","Lauflabor Locomotion Laboratory, Institute of Sport Science, TU Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Sport Science,Lauflabor Locomotion Laboratory,TU Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210095579"]},{"raw_affiliation_string":"Lauflabor Locomotion Laboratory, Institute of Sport Science, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210095579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088706700","display_name":"Boris Belousov","orcid":"https://orcid.org/0000-0001-7172-9104"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Boris Belousov","raw_affiliation_strings":["Intelligent Autonomous Systems Lab,Department of Computer Science,TU Darmstadt,Germany","Department of Computer Science, Intelligent Autonomous Systems Lab, TU Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Lab,Department of Computer Science,TU Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, Intelligent Autonomous Systems Lab, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015080938","display_name":"Andr\u00e9 Seyfarth","orcid":"https://orcid.org/0000-0001-8285-2415"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210095579","display_name":"Institute for Sports Medicine","ror":"https://ror.org/0084rd854","country_code":"DE","type":"other","lineage":["https://openalex.org/I4210095579"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andre Seyfarth","raw_affiliation_strings":["Institute of Sport Science,Lauflabor Locomotion Laboratory,TU Darmstadt,Germany","Lauflabor Locomotion Laboratory, Institute of Sport Science, TU Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Sport Science,Lauflabor Locomotion Laboratory,TU Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210095579"]},{"raw_affiliation_string":"Lauflabor Locomotion Laboratory, Institute of Sport Science, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210095579"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems Lab,Department of Computer Science,TU Darmstadt,Germany","Department of Computer Science, Intelligent Autonomous Systems Lab, TU Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Lab,Department of Computer Science,TU Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, Intelligent Autonomous Systems Lab, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9947999715805054,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8563101291656494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7317272424697876},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6623054146766663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5600327253341675},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.542632520198822},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.506962776184082},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5009632110595703},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4557279646396637},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4345674514770508},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42757949233055115},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.16492822766304016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1056194007396698}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8563101291656494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7317272424697876},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6623054146766663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600327253341675},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.542632520198822},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.506962776184082},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5009632110595703},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4557279646396637},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4345674514770508},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42757949233055115},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.16492822766304016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1056194007396698},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids53995.2022.10000068","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/humanoids53995.2022.10000068","pdf_url":null,"source":{"id":"https://openalex.org/S4363608580","display_name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4007599710","display_name":null,"funder_award_id":"SE 1042/41-1,PE 2315/14-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1986621758","https://openalex.org/W2018860673","https://openalex.org/W2111966261","https://openalex.org/W2161427949","https://openalex.org/W2726187156","https://openalex.org/W2729615412","https://openalex.org/W2736601468","https://openalex.org/W2747329762","https://openalex.org/W2784449021","https://openalex.org/W2796290181","https://openalex.org/W2904246096","https://openalex.org/W2911087563","https://openalex.org/W2954996726","https://openalex.org/W2958043083","https://openalex.org/W2964114602","https://openalex.org/W2977389550","https://openalex.org/W2981030070","https://openalex.org/W2981479926","https://openalex.org/W3002258670","https://openalex.org/W3006422628","https://openalex.org/W3007035358","https://openalex.org/W3010781003","https://openalex.org/W3022566517","https://openalex.org/W3035700320","https://openalex.org/W3039737909","https://openalex.org/W3048846969","https://openalex.org/W3092277419","https://openalex.org/W3104515094","https://openalex.org/W3104883169","https://openalex.org/W3105609823","https://openalex.org/W3108144771","https://openalex.org/W3207491493","https://openalex.org/W4300892751","https://openalex.org/W4311443585","https://openalex.org/W6757592117","https://openalex.org/W6772196467","https://openalex.org/W6776438516","https://openalex.org/W6779282036","https://openalex.org/W6782443645"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W2129850190","https://openalex.org/W4256317079","https://openalex.org/W2295425790","https://openalex.org/W1991876829","https://openalex.org/W4389009354","https://openalex.org/W1974803039","https://openalex.org/W2088677124","https://openalex.org/W1589423663","https://openalex.org/W2143454724"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"holds":[2],"a":[3,46,61,70,107],"great":[4],"promise":[5],"of":[6,23,31,48,54,74,88,109],"enabling":[7],"bipedal":[8,89],"walking":[9],"in":[10,64,131],"humanoid":[11],"robots.":[12],"However,":[13],"despite":[14],"encouraging":[15],"recent":[16],"results,":[17],"training":[18,37,65,123],"still":[19],"requires":[20],"significant":[21,62],"amounts":[22],"time":[24,66],"and":[25,58,81,97,125],"resources,":[26],"precluding":[27],"fast":[28],"iteration":[29],"cycles":[30,130],"the":[32,75,86],"control":[33],"development.":[34],"Therefore,":[35],"faster":[36,128],"methods":[38],"are":[39],"needed.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"investigate":[45],"number":[47],"techniques":[49],"for":[50],"improving":[51],"sample":[52,104],"efficiency":[53],"on-policy":[55],"actor-critic":[56],"algorithms":[57],"show":[59],"that":[60,114],"reduction":[63],"is":[67],"achievable":[68],"with":[69],"few":[71],"straightforward":[72],"modifications":[73],"common":[76],"algorithms,":[77],"such":[78],"as":[79],"PPO":[80],"DeepMimic,":[82],"tailored":[83],"specifically":[84],"towards":[85],"problem":[87],"walking.":[90],"Action":[91],"space":[92],"representation,":[93],"symmetry":[94],"prior":[95],"induction,":[96],"cliprange":[98],"scheduling":[99],"proved":[100],"effective":[101],"at":[102],"reducing":[103],"complexity":[105],"by":[106],"factor":[108],"4.5.":[110],"These":[111],"results":[112],"indicate":[113],"domain-specific":[115],"knowledge":[116],"can":[117],"be":[118],"readily":[119],"utilized":[120],"to":[121],"reduce":[122],"times":[124],"thereby":[126],"enable":[127],"development":[129],"challenging":[132],"robotic":[133],"applications.":[134]},"counts_by_year":[],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}