{"id":"https://openalex.org/W2011900082","doi":"https://doi.org/10.1109/icsmc.2010.5642195","title":"High-level behavior control of an e-pet with reinforcement learning","display_name":"High-level behavior control of an e-pet with reinforcement learning","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2011900082","doi":"https://doi.org/10.1109/icsmc.2010.5642195","mag":"2011900082"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2010.5642195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2010.5642195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Systems, Man and Cybernetics","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/A5101930378","display_name":"Chih\u2010Wei Hsu","orcid":"https://orcid.org/0000-0001-9929-9951"},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Wei Hsu","raw_affiliation_strings":["MeeGo Group, Institute for Information Industry, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"MeeGo Group, Institute for Information Industry, Tainan, Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101726185","display_name":"Alan Liu","orcid":"https://orcid.org/0000-0002-8884-6662"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Alan Liu","raw_affiliation_strings":["Department of Electrical Engineering, Center of Telecommunication Research, National Chung Cheng University, Chiayi, Taiwan","Department of Electrical Engineering, Center for Telecommunication Research, National Chung Cheng University, Chiayi, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Center of Telecommunication Research, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]},{"raw_affiliation_string":"Department of Electrical Engineering, Center for Telecommunication Research, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101930378"],"corresponding_institution_ids":["https://openalex.org/I3141939062"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09113238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"29","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9745000004768372,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8405921459197998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415164709091187},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7228370308876038},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6490235328674316},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6145223379135132},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.6033627390861511},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5499361753463745},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5230092406272888},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5134969353675842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5060679316520691},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4295434057712555},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4045883119106293},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3370051383972168},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3321760892868042},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.20918402075767517},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1321045160293579}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8405921459197998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415164709091187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7228370308876038},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6490235328674316},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6145223379135132},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6033627390861511},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5499361753463745},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5230092406272888},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5134969353675842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5060679316520691},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4295434057712555},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4045883119106293},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3370051383972168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3321760892868042},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.20918402075767517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1321045160293579},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2010.5642195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2010.5642195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1550294342","https://openalex.org/W2006353717","https://openalex.org/W2097856935","https://openalex.org/W2147357263","https://openalex.org/W2161521419","https://openalex.org/W6683639705"],"related_works":["https://openalex.org/W3123911006","https://openalex.org/W4400868993","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2386410636"],"abstract_inverted_index":{"One":[0],"of":[1,4,33,58,99],"attractive":[2],"features":[3],"electronic-pets":[5],"(e-pets)":[6],"is":[7,18,61,93,109],"interaction":[8],"between":[9],"the":[10,13,23,35,56,59,82,97,100,104],"user":[11,36],"and":[12,55,81,115],"e-pet.":[14],"The":[15,48],"interaction,":[16],"however,":[17],"usually":[19],"limited":[20],"to":[21,96,111],"using":[22],"predefined":[24],"commands.":[25],"In":[26,67],"this":[27,68],"paper,":[28],"we":[29,70,73],"present":[30],"a":[31,75],"way":[32],"involving":[34],"in":[37],"helping":[38],"an":[39],"e-pet":[40,101],"learn":[41],"high-level":[42,49],"behaviors":[43,50,60],"based":[44],"on":[45],"basic":[46],"actions.":[47],"are":[51],"derived":[52],"with":[53,64],"planning,":[54],"execution":[57],"then":[62,94],"trained":[63],"reinforcement":[65],"learning.":[66],"research,":[69],"explain":[71],"how":[72],"use":[74],"partially":[76],"observable":[77],"Markov":[78],"decision":[79],"process":[80],"hierarchical":[83],"task":[84],"network":[85],"planning":[86],"for":[87,102],"designing":[88],"behaviors.":[89],"A":[90,107],"Q-learning":[91],"method":[92],"applied":[95],"training":[98],"achieving":[103],"correct":[105],"behavior.":[106],"prototype":[108],"presented":[110],"show":[112],"its":[113],"feasibility":[114],"effectiveness.":[116]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}