{"id":"https://openalex.org/W2752941321","doi":"https://doi.org/10.1109/icar.2017.8023674","title":"Model-based Q-learning for humanoid robots","display_name":"Model-based Q-learning for humanoid robots","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2752941321","doi":"https://doi.org/10.1109/icar.2017.8023674","mag":"2752941321"},"language":"en","primary_location":{"id":"doi:10.1109/icar.2017.8023674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar.2017.8023674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 18th International Conference on Advanced Robotics (ICAR)","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/A5043412244","display_name":"Than Le","orcid":"https://orcid.org/0000-0002-7551-0756"},"institutions":[{"id":"https://openalex.org/I4210125057","display_name":"Vivekananda Global University","ror":"https://ror.org/038mz4r36","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210125057"]},{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB","IN"],"is_corresponding":true,"raw_author_name":"Than D. Le","raw_affiliation_strings":["Faculty of Engineering, VGU","UWE, Bristol Robotics Laboratory"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, VGU","institution_ids":["https://openalex.org/I4210125057"]},{"raw_affiliation_string":"UWE, Bristol Robotics Laboratory","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102888876","display_name":"An T. Le","orcid":"https://orcid.org/0000-0003-0929-3316"},"institutions":[{"id":"https://openalex.org/I4210125057","display_name":"Vivekananda Global University","ror":"https://ror.org/038mz4r36","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210125057"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"An T. Le","raw_affiliation_strings":["Faculty of Engineering, VGU"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, VGU","institution_ids":["https://openalex.org/I4210125057"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110523477","display_name":"Duy Thao Nguyen","orcid":"https://orcid.org/0009-0007-0050-5606"},"institutions":[{"id":"https://openalex.org/I4210125057","display_name":"Vivekananda Global University","ror":"https://ror.org/038mz4r36","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210125057"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Duy T. Nguyen","raw_affiliation_strings":["Faculty of Engineering, VGU"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, VGU","institution_ids":["https://openalex.org/I4210125057"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043412244"],"corresponding_institution_ids":["https://openalex.org/I4210125057","https://openalex.org/I4210161128"],"apc_list":null,"apc_paid":null,"fwci":1.5602,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.874343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"ii","issue":null,"first_page":"608","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.989799976348877,"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":0.989799976348877,"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":0.9603999853134155,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.954200029373169,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.8264168500900269},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7459006309509277},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.7261322736740112},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6981224417686462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6806763410568237},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6621991395950317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6332288980484009},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5862351059913635},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4683237671852112},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3675466775894165},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3569401204586029}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.8264168500900269},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7459006309509277},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.7261322736740112},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6981224417686462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6806763410568237},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6621991395950317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6332288980484009},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5862351059913635},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4683237671852112},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3675466775894165},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3569401204586029}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icar.2017.8023674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar.2017.8023674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 18th International Conference on Advanced Robotics (ICAR)","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":14,"referenced_works":["https://openalex.org/W755046805","https://openalex.org/W1515851193","https://openalex.org/W1601081659","https://openalex.org/W1977655452","https://openalex.org/W2024780670","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2117726420","https://openalex.org/W2131600418","https://openalex.org/W2162602080","https://openalex.org/W2787259794","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4362203700"],"related_works":["https://openalex.org/W2543019745","https://openalex.org/W2531662632","https://openalex.org/W4247750500","https://openalex.org/W2540452882","https://openalex.org/W2356070666","https://openalex.org/W2778262232","https://openalex.org/W2151682110","https://openalex.org/W4386128912","https://openalex.org/W2910269320","https://openalex.org/W2152492056"],"abstract_inverted_index":{"This":[0,60],"paper":[1,61],"is":[2,32],"proposal":[3],"with":[4],"regarding":[5],"reinforcement":[6,17],"learning":[7,18],"and":[8,20,40,69,74,93],"robotics.":[9],"It":[10],"contains":[11],"our":[12,64,75],"study":[13],"so":[14],"far":[15],"about":[16,66],"problem":[19],"Q-learning":[21,79,91],"-":[22],"one":[23],"of":[24],"the":[25,52,84],"methods":[26],"to":[27,77,96],"solve":[28],"it.":[29],"The":[30],"method":[31,92],"tested":[33,90],"both":[34],"by":[35],"running":[36],"on":[37,41,57,80],"a":[38],"simulation":[39],"NAO":[42,58,67,81,97],"robot.":[43,59,82],"Both":[44],"are":[45,54],"written":[46],"in":[47,99],"high":[48],"programming":[49],"language.":[50],"Since":[51],"testing":[53],"also":[55,62],"done":[56],"includes":[63],"understanding":[65],"robot":[68,98],"Robotic":[70],"Operating":[71],"System":[72],"(ROS),":[73],"approach":[76],"apply":[78,94],"In":[83],"end,":[85],"we":[86],"have":[87],"been":[88],"successfully":[89],"it":[95],"real-world":[100],"environment.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}