{"id":"https://openalex.org/W4312933601","doi":"https://doi.org/10.1109/iros47612.2022.9981749","title":"Distributed Coach-Based Reinforcement Learning Controller for Snake Robot Locomotion","display_name":"Distributed Coach-Based Reinforcement Learning Controller for Snake Robot Locomotion","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312933601","doi":"https://doi.org/10.1109/iros47612.2022.9981749"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981749","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100669026","display_name":"Yuanyuan Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuanyuan Jia","raw_affiliation_strings":["Ritsumeikan University,Department of Robotics,Kusatsu,Shiga,Japan,525-8577"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Department of Robotics,Kusatsu,Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102150334","display_name":"Shugen Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shugen Ma","raw_affiliation_strings":["Ritsumeikan University,Department of Robotics,Kusatsu,Shiga,Japan,525-8577"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Department of Robotics,Kusatsu,Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100669026"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.33187891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9886000156402588,"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":0.9886000156402588,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9837999939918518,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8192949295043945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117618322372437},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6994966268539429},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6564978361129761},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5884619355201721},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5695503354072571},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4800927937030792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46946895122528076},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4347136914730072},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4229307770729065},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.42094850540161133},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3690698742866516},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3018825650215149},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17066815495491028}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8192949295043945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117618322372437},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6994966268539429},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6564978361129761},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5884619355201721},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5695503354072571},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4800927937030792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46946895122528076},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4347136914730072},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4229307770729065},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.42094850540161133},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3690698742866516},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3018825650215149},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17066815495491028},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981749","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W186521003","https://openalex.org/W1573670163","https://openalex.org/W1739716134","https://openalex.org/W2794308328","https://openalex.org/W2912971983","https://openalex.org/W2963873508","https://openalex.org/W3100789280","https://openalex.org/W3103532359","https://openalex.org/W3123298421","https://openalex.org/W3132175036","https://openalex.org/W3182595669","https://openalex.org/W4299828299","https://openalex.org/W4388323202","https://openalex.org/W6617145748","https://openalex.org/W6680657880","https://openalex.org/W6779886872"],"related_works":["https://openalex.org/W1886477626","https://openalex.org/W2762381663","https://openalex.org/W4385196987","https://openalex.org/W1540467731","https://openalex.org/W218732962","https://openalex.org/W2538037439","https://openalex.org/W4317826762","https://openalex.org/W2741909783","https://openalex.org/W1979383880","https://openalex.org/W4210919297"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,64],"commonly":[2],"suffers":[3],"from":[4],"slow":[5],"convergence":[6],"speed":[7,76],"and":[8,114],"requires":[9],"thousands":[10],"of":[11,36,40,43,111],"episodes,":[12],"which":[13,70],"makes":[14],"it":[15],"hard":[16],"to":[17],"be":[18],"applied":[19],"for":[20,29,66,97],"physical":[21],"robotic":[22],"applications.":[23],"Little":[24],"research":[25],"has":[26],"been":[27],"studied":[28],"snake":[30,67],"robot":[31,68,99],"control":[32],"using":[33],"RL":[34],"because":[35],"the":[37,74,119],"additional":[38],"difficulty":[39],"high":[41],"redundancy":[42],"freedom.":[44],"Existing":[45],"methods":[46],"either":[47],"adopts":[48],"an":[49,91],"asynchronous":[50],"A3C":[51],"structure":[52],"or":[53],"a":[54,60,85],"joint":[55],"state":[56],"representation.":[57],"We":[58],"propose":[59],"distributed":[61,87],"coach-based":[62],"deep":[63],"method":[65],"control,":[69],"can":[71],"greatly":[72],"expedite":[73],"training":[75],"with":[77,105,124],"less":[78],"episodes.":[79],"The":[80,108],"major":[81],"contributions":[82],"include:":[83],"1)":[84],"completely":[86],"graphical":[88],"formulation;":[89],"2)":[90],"explicit":[92],"stochastic":[93],"density":[94],"propagation":[95],"rule":[96],"each":[98],"link;":[100],"3)":[101],"various":[102],"interaction":[103],"models":[104],"uncertainty":[106],"estimation.":[107],"preliminary":[109],"results":[110],"both":[112],"simulation":[113],"real-world":[115],"experiments":[116],"have":[117],"demonstrated":[118],"promising":[120],"performance":[121],"in":[122],"comparison":[123],"state-of-the-art.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
