{"id":"https://openalex.org/W3197516770","doi":"https://doi.org/10.1145/3461353.3461373","title":"A Domain Data Pattern Randomization based Deep Reinforcement Learning method for Sim-to-Real transfer","display_name":"A Domain Data Pattern Randomization based Deep Reinforcement Learning method for Sim-to-Real transfer","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3197516770","doi":"https://doi.org/10.1145/3461353.3461373","mag":"3197516770"},"language":"en","primary_location":{"id":"doi:10.1145/3461353.3461373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461353.3461373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","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/A5026199735","display_name":"Peng Gong","orcid":"https://orcid.org/0000-0001-6352-1696"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Gong","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["National Innovation Institute of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National Innovation Institute of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100884245","display_name":"Chao Xue","orcid":"https://orcid.org/0000-0002-9507-9991"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Xue","raw_affiliation_strings":["National Innovation Institute of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National Innovation Institute of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031813784","display_name":"Xucan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xucan Chen","raw_affiliation_strings":["National Innovation Institute of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National Innovation Institute of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026199735"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12213293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9688000082969666,"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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9534000158309937,"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/computer-science","display_name":"Computer science","score":0.7461162209510803},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6985180377960205},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.6133091449737549},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5590500235557556},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5236912965774536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4973790943622589},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4877665638923645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46011075377464294},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4392913579940796},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43124476075172424},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42860984802246094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32889097929000854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461162209510803},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6985180377960205},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.6133091449737549},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5590500235557556},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5236912965774536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4973790943622589},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4877665638923645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46011075377464294},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4392913579940796},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43124476075172424},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42860984802246094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32889097929000854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461353.3461373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461353.3461373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2165150801","https://openalex.org/W2167340365","https://openalex.org/W2530944449","https://openalex.org/W2534269850","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2890755534","https://openalex.org/W2925306934","https://openalex.org/W2963201472","https://openalex.org/W2968638474","https://openalex.org/W2990747716","https://openalex.org/W3030141984","https://openalex.org/W3037262181","https://openalex.org/W3088310808","https://openalex.org/W3090612618","https://openalex.org/W3101442004","https://openalex.org/W3120778962","https://openalex.org/W3130451601","https://openalex.org/W3200385828"],"related_works":["https://openalex.org/W2121182846","https://openalex.org/W2155789024","https://openalex.org/W2315668284","https://openalex.org/W3213608175","https://openalex.org/W3117675750","https://openalex.org/W2141743053","https://openalex.org/W2109491806","https://openalex.org/W3095633856","https://openalex.org/W2058044441","https://openalex.org/W3171384686"],"abstract_inverted_index":{"Transferring":[0],"reinforcement":[1],"learning":[2],"policies":[3,81],"trained":[4],"in":[5,34,97,170],"a":[6,14,110],"physical":[7],"simulator":[8],"to":[9,31,46,48,61,84,148,162],"the":[10,19,22,28,35,50,63,66,86,98,102,124,131,134,145,150,164,168,176],"real":[11,36],"world":[12],"is":[13,142],"highly":[15],"challenging":[16],"problem,":[17,107],"because":[18],"gap":[20,51],"between":[21,52],"simulation":[23,53],"and":[24,54],"reality,":[25],"usually":[26],"causes":[27],"transferred":[29],"model":[30],"perform":[32],"poorly":[33],"world.":[37],"Many":[38],"algorithms":[39],"including":[40],"domain":[41,112],"randomization,":[42],"have":[43],"been":[44],"proposed":[45,109],"try":[47],"bridge":[49],"reality.":[55],"However,":[56],"most":[57],"of":[58,65,88,101,127,152,167,178],"them":[59],"are":[60],"change":[62,177],"value":[64],"corresponding":[67],"data":[68,91,113,120,128,157,179],"by":[69,94,122,156,175],"superimposing":[70],"gaussian":[71],"noise":[72],"on":[73,138],"robot":[74,169],"dynamics":[75],"parameters":[76],"or":[77],"environmental":[78,153],"data.":[79],"Such":[80],"often":[82],"fail":[83],"solve":[85],"problem":[87],"long-term/intermittent":[89],"missing":[90],"patterns":[92],"caused":[93,155],"sensor":[95],"failures":[96],"actual":[99],"operation":[100],"robot.":[103],"Faced":[104],"with":[105],"this":[106],"we":[108],"memory-enhanced":[111],"pattern":[114,126,158],"randomization":[115],"method.":[116],"This":[117],"method":[118],"achieves":[119],"enhancement":[121],"randomizing":[123],"distribution":[125,154],"connection,":[129],"at":[130],"same":[132],"time,":[133],"memory":[135],"mechanism":[136],"based":[137],"recurrent":[139],"neural":[140],"network":[141],"introduced":[143],"into":[144],"decision":[146],"model,":[147],"alleviate":[149],"jitter":[151],"changes,":[159],"so":[160],"as":[161],"improve":[163],"decision-making":[165],"ability":[166],"some":[171],"observable":[172],"scenes":[173],"triggered":[174],"pattern.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}