{"id":"https://openalex.org/W3140464672","doi":"https://doi.org/10.1145/3445815.3445836","title":"A Reward Shaping Method based on Meta-LSTM for Continuous Control of Robot","display_name":"A Reward Shaping Method based on Meta-LSTM for Continuous Control of Robot","publication_year":2020,"publication_date":"2020-12-11","ids":{"openalex":"https://openalex.org/W3140464672","doi":"https://doi.org/10.1145/3445815.3445836","mag":"3140464672"},"language":"en","primary_location":{"id":"doi:10.1145/3445815.3445836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445815.3445836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 4th International Conference on Computer Science and 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/A5015560758","display_name":"Jixun Yao","orcid":"https://orcid.org/0000-0002-5324-7360"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixun Yao","raw_affiliation_strings":["School of Computer Science and Technology Northwestern Polytechnical University, Xi'an Shaanxi 710072 P. R., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology Northwestern Polytechnical University, Xi'an Shaanxi 710072 P. R., China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066445519","display_name":"Xiaoan Li","orcid":"https://orcid.org/0009-0006-8293-8845"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoan Li","raw_affiliation_strings":["School of Computer Science and Technology Northwestern Polytechnical University, Xi'an Shaanxi 710072 P. R., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology Northwestern Polytechnical University, Xi'an Shaanxi 710072 P. R., China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050722993","display_name":"Dengshan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengshan Huang","raw_affiliation_strings":["School of Computer Science and Technology Northwestern Polytechnical University, Xi'an Shaanxi 710072 P. R., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology Northwestern Polytechnical University, Xi'an Shaanxi 710072 P. R., China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22138791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.9246000051498413,"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":0.8943445682525635},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7391045689582825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7127740979194641},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6576316356658936},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6128128170967102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5853201150894165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5684798955917358},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5520657300949097},{"id":"https://openalex.org/keywords/promotion","display_name":"Promotion (chess)","score":0.525151252746582},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4843353033065796},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.47701001167297363},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4645654261112213},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46230900287628174},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45222264528274536},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42374980449676514},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11796966195106506}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8943445682525635},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7391045689582825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127740979194641},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6576316356658936},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6128128170967102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853201150894165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5684798955917358},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5520657300949097},{"id":"https://openalex.org/C98147612","wikidata":"https://www.wikidata.org/wiki/Q215599","display_name":"Promotion (chess)","level":3,"score":0.525151252746582},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4843353033065796},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.47701001167297363},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4645654261112213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46230900287628174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45222264528274536},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42374980449676514},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11796966195106506},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/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},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3445815.3445836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445815.3445836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 4th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2729602312","https://openalex.org/W2895279298","https://openalex.org/W2991015479","https://openalex.org/W2999714443","https://openalex.org/W6605730092"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W3130669838","https://openalex.org/W2341346307","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321"],"abstract_inverted_index":{"In":[0],"the":[1,23,27,34,37,41,46,62,68,71,81,89,94,106,110,116,121,125,132],"continuous":[2],"control":[3],"of":[4,36,70,83,96],"robots":[5],"based":[6,60,108],"on":[7,40,61,80,109],"reinforcement":[8,19],"learning,":[9],"Proximal":[10],"Policy":[11],"Optimization":[12],"(PPO)":[13],"is":[14,64,113,128],"a":[15,56],"highly":[16],"popular":[17],"policy-based":[18],"learning":[20,72],"algorithm.":[21],"However,":[22],"PPO":[24],"algorithm":[25,59,118],"reduces":[26],"policy":[28,42,47,122],"update":[29],"area":[30],"prematurely":[31],"due":[32],"to":[33,49,92,98],"influence":[35],"advantage":[38],"function":[39],"search,":[43,123],"which":[44],"causes":[45],"search":[48],"progress":[50],"slowly.":[51],"Drawing":[52],"inspiration":[53],"from":[54],"meta-learning,":[55],"reward":[57,73,97,107],"shaping":[58,74],"Meta-LSTM":[63,86,111],"proposed.":[65],"To":[66],"ensure":[67,93],"stability":[69],"process,":[75],"we":[76],"innovatively":[77],"added":[78],"constraints":[79],"importance":[82],"actions":[84],"in":[85,119,131],"and":[87,124],"through":[88],"motivate":[90],"coefficient":[91],"adaptability":[95],"different":[99],"environments.":[100],"The":[101],"experimental":[102],"results":[103],"show":[104],"that":[105],"method":[112],"better":[114],"than":[115],"benchmark":[117],"guiding":[120],"promotion":[126],"effect":[127],"more":[129],"evident":[130],"task":[133],"with":[134],"higher":[135],"dimensions.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}