{"id":"https://openalex.org/W4312375217","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892913","title":"Exploring Coarse-grained Pre-guided Attention to Assist Fine-grained Attention Reinforcement Learning Agents","display_name":"Exploring Coarse-grained Pre-guided Attention to Assist Fine-grained Attention Reinforcement Learning Agents","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312375217","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892913"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892913","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","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/A5007122963","display_name":"Haoyu Liu","orcid":"https://orcid.org/0000-0002-0839-5460"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Liu","raw_affiliation_strings":["Renmin University of China,School of Statistics,Beijing,China","School of Statistics, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Statistics,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Statistics, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Language Understanding Lab Samsung Research China,Beijing,China","Language Understanding Lab Samsung Research China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Language Understanding Lab Samsung Research China,Beijing,China","institution_ids":["https://openalex.org/I4210155230"]},{"raw_affiliation_string":"Language Understanding Lab Samsung Research China, Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103126299","display_name":"Xingrui Wang","orcid":"https://orcid.org/0000-0003-0480-2302"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingrui Wang","raw_affiliation_strings":["Renmin University of China,School of Statistics,Beijing,China","School of Statistics, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Statistics,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Statistics, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084917712","display_name":"Hanfang Yang","orcid":"https://orcid.org/0000-0002-0983-6758"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanfang Yang","raw_affiliation_strings":["Renmin University of China,School of Statistics,Beijing,China","School of Statistics, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Statistics,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Statistics, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007122963"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3175501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9966999888420105,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.8379883766174316},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8243426084518433},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6679254770278931},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5627313256263733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.531599760055542},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5315273404121399},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4133497476577759},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37580108642578125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379883766174316},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8243426084518433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6679254770278931},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5627313256263733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531599760055542},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5315273404121399},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4133497476577759},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37580108642578125},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/ijcnn55064.2022.9892913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892913","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1526641569","https://openalex.org/W1580222235","https://openalex.org/W1581202840","https://openalex.org/W2033859430","https://openalex.org/W2131600418","https://openalex.org/W2195446438","https://openalex.org/W2302086703","https://openalex.org/W2564920024","https://openalex.org/W2730246242","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2749928749","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2771807014","https://openalex.org/W2891830784","https://openalex.org/W2902729397","https://openalex.org/W2922282711","https://openalex.org/W2949615363","https://openalex.org/W2950395671","https://openalex.org/W2963513865","https://openalex.org/W2964043796","https://openalex.org/W2964053787","https://openalex.org/W2997423597","https://openalex.org/W3004058922","https://openalex.org/W3080447155","https://openalex.org/W3096818755","https://openalex.org/W3100789280","https://openalex.org/W3101780148","https://openalex.org/W3119860245","https://openalex.org/W3164815450","https://openalex.org/W3192863538","https://openalex.org/W4295720520","https://openalex.org/W4297797010","https://openalex.org/W4385245566","https://openalex.org/W6632455782","https://openalex.org/W6687590523","https://openalex.org/W6692846177","https://openalex.org/W6731192180","https://openalex.org/W6735579001","https://openalex.org/W6739901393","https://openalex.org/W6740661740","https://openalex.org/W6741002519","https://openalex.org/W6743802245","https://openalex.org/W6746042458","https://openalex.org/W6748638692","https://openalex.org/W6749972507","https://openalex.org/W6763704883","https://openalex.org/W6781615458","https://openalex.org/W6783777085","https://openalex.org/W6799590645"],"related_works":["https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2021400925","https://openalex.org/W2945115303","https://openalex.org/W4288348115","https://openalex.org/W2774891019","https://openalex.org/W2077154395","https://openalex.org/W4287626175","https://openalex.org/W3122543654","https://openalex.org/W2343515139"],"abstract_inverted_index":{"Recently,":[0],"people":[1],"have":[2],"applied":[3],"the":[4,23,34,66,69,79,107,132,172,178,220],"attention":[5,36,41,47,76,89,98,103,116,128,135,142,158,182,208,222,243,250],"mechanism":[6],"to":[7,14,21,58,77,86,130,212,245],"deep":[8],"reinforcement":[9],"learning":[10],"(DRL),":[11],"which":[12,119,218],"commits":[13],"helping":[15],"agents":[16,199],"focus":[17],"on":[18],"crucial":[19],"factors":[20,64],"learn":[22,78],"task":[24,70],"more":[25,90,213],"effectively.":[26],"However,":[27],"there":[28],"is":[29,153],"still":[30],"some":[31],"margin":[32],"between":[33],"current":[35,179],"methods":[37,183],"and":[38,71,152,175,237],"natural":[39],"human":[40,46,102,124,190,242],"since":[42],"evidence":[43],"suggests":[44,219],"that":[45,100,164,240],"can":[48,167,200],"be":[49],"pre-guided":[50,126,207,221],"before":[51],"they":[52],"perform":[53],"a":[54,114,122,156,226,235],"task,":[55],"allowing":[56],"humans":[57,85],"quickly":[59,168],"catch":[60],"areas":[61],"of":[62,68,136,206],"important":[63],"at":[65],"beginning":[67],"then":[72,176],"gradually":[73],"refine":[74],"fine-grained":[75,134,181],"details":[80],"during":[81],"training.":[82],"This":[83],"allows":[84],"use":[87],"their":[88],"efficiently.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95,120,230],"propose":[96],"an":[97],"method":[99,112,166],"mimics":[101],"for":[104,118,149],"DRL":[105],"in":[106,171,185],"Atari":[108],"Games.":[109],"The":[110,139,160],"proposed":[111,140],"contains":[113,144],"fusion":[115,197],"module,":[117],"build":[121],"simulated":[123],"coarse-grained":[125,157],"(SHCP)":[127],"module":[129,143],"assist":[131],"original":[133],"RL":[137],"agents.":[138],"SHCP":[141],"information":[145],"about":[146],"key":[147],"objects":[148],"game":[150],"tasks":[151],"implemented":[154],"as":[155,225],"region.":[159],"experimental":[161],"results":[162],"demonstrate":[163],"our":[165,232],"boost":[169],"performance":[170],"early":[173],"stages":[174],"outperform":[177],"state-of-the-art":[180],"significantly":[184],"sample":[186],"efficiency,":[187],"just":[188],"like":[189],"attention.":[191],"Further":[192],"analysis":[193],"shows":[194],"that,":[195],"with":[196],"attention,":[198],"not":[201],"only":[202],"capture":[203],"rich":[204],"features":[205,215],"but":[209],"also":[210],"extend":[211],"improved":[214],"after":[216],"training,":[217],"signal":[223],"acts":[224],"good":[227],"initializer.":[228],"Therefore,":[229],"consider":[231],"work":[233],"reveals":[234],"potential":[236],"promising":[238],"direction":[239],"combines":[241],"signals":[244],"affect":[246],"agents'":[247],"behavior":[248],"via":[249],"mechanisms.":[251]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}