{"id":"https://openalex.org/W2171128163","doi":"https://doi.org/10.1109/robio.2010.5723536","title":"Human-like gradual learning of a Q-learning based Light exploring robot","display_name":"Human-like gradual learning of a Q-learning based Light exploring robot","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2171128163","doi":"https://doi.org/10.1109/robio.2010.5723536","mag":"2171128163"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2010.5723536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2010.5723536","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 Robotics and Biomimetics","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/A5104022224","display_name":"Dip Narayan Ray","orcid":"https://orcid.org/0009-0002-2308-7850"},"institutions":[{"id":"https://openalex.org/I70735523","display_name":"Central Mechanical Engineering Research Institute","ror":"https://ror.org/059h0ng81","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702","https://openalex.org/I70735523"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dip N Ray","raw_affiliation_strings":["Surface Robotics Laboratory, Central Mechanical Engineering Research Institute, Durgapur, India"],"affiliations":[{"raw_affiliation_string":"Surface Robotics Laboratory, Central Mechanical Engineering Research Institute, Durgapur, India","institution_ids":["https://openalex.org/I70735523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074742889","display_name":"Amit Kr Mandal","orcid":"https://orcid.org/0000-0001-6579-118X"},"institutions":[{"id":"https://openalex.org/I70735523","display_name":"Central Mechanical Engineering Research Institute","ror":"https://ror.org/059h0ng81","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702","https://openalex.org/I70735523"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Mandal","raw_affiliation_strings":["Surface Robotics Laboratory, CMERI, Durgapur, India"],"affiliations":[{"raw_affiliation_string":"Surface Robotics Laboratory, CMERI, Durgapur, India","institution_ids":["https://openalex.org/I70735523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102184245","display_name":"Somajyoti Majumder","orcid":null},"institutions":[{"id":"https://openalex.org/I70735523","display_name":"Central Mechanical Engineering Research Institute","ror":"https://ror.org/059h0ng81","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702","https://openalex.org/I70735523"]},{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU","IN"],"is_corresponding":false,"raw_author_name":"Somajyoti Majumder","raw_affiliation_strings":["Surface Robotics Laboratory, CMERI, Durgapur, India","University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Surface Robotics Laboratory, CMERI, Durgapur, India","institution_ids":["https://openalex.org/I70735523"]},{"raw_affiliation_string":"University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102057001","display_name":"Sumit Mukhopadhyay","orcid":null},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Mukhopadhyay","raw_affiliation_strings":["Department of Mechanical Engineering, National Institute of Technology, Durgapur, India"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, National Institute of Technology, Durgapur, India","institution_ids":["https://openalex.org/I155837530"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104022224"],"corresponding_institution_ids":["https://openalex.org/I70735523"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.15261653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1411","last_page":"1416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9897000193595886,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9897000193595886,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9879999756813049,"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/T10320","display_name":"Neural Networks and Applications","score":0.986299991607666,"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/robot-learning","display_name":"Robot learning","score":0.7629609107971191},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7136675119400024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.693631649017334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6742934584617615},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6562063694000244},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.6388071179389954},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.604216456413269},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5798217058181763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5523428320884705},{"id":"https://openalex.org/keywords/action-learning","display_name":"Action learning","score":0.5496096611022949},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.5465973019599915},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.5126411318778992},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4813143014907837},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4784255623817444},{"id":"https://openalex.org/keywords/proactive-learning","display_name":"Proactive learning","score":0.45880261063575745},{"id":"https://openalex.org/keywords/competitive-learning","display_name":"Competitive learning","score":0.44108492136001587},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4366607666015625},{"id":"https://openalex.org/keywords/algorithmic-learning-theory","display_name":"Algorithmic learning theory","score":0.41246798634529114},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3777921795845032},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.3670181334018707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1746724545955658},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.10731247067451477},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.08028638362884521}],"concepts":[{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.7629609107971191},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7136675119400024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.693631649017334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6742934584617615},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6562063694000244},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.6388071179389954},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.604216456413269},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5798217058181763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5523428320884705},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.5496096611022949},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.5465973019599915},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.5126411318778992},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4813143014907837},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4784255623817444},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.45880261063575745},{"id":"https://openalex.org/C120822770","wikidata":"https://www.wikidata.org/wiki/Q5156355","display_name":"Competitive learning","level":3,"score":0.44108492136001587},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4366607666015625},{"id":"https://openalex.org/C32254414","wikidata":"https://www.wikidata.org/wiki/Q4724364","display_name":"Algorithmic learning theory","level":3,"score":0.41246798634529114},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3777921795845032},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.3670181334018707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1746724545955658},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.10731247067451477},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.08028638362884521},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2010.5723536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2010.5723536","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 Robotics and Biomimetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335900","display_name":"Central Mechanical Engineering Research Institute, Council of Scientific and Industrial Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W89091142","https://openalex.org/W115366556","https://openalex.org/W1489823842","https://openalex.org/W1491843047","https://openalex.org/W1500245617","https://openalex.org/W1557517019","https://openalex.org/W1562437701","https://openalex.org/W1587234450","https://openalex.org/W1987864653","https://openalex.org/W1989424791","https://openalex.org/W2032252420","https://openalex.org/W2107726111","https://openalex.org/W2110771465","https://openalex.org/W2116339808","https://openalex.org/W2117514361","https://openalex.org/W2121863487","https://openalex.org/W2132064930","https://openalex.org/W2142270171","https://openalex.org/W2156423174","https://openalex.org/W2159642572","https://openalex.org/W2170052867","https://openalex.org/W2610686804","https://openalex.org/W2742347120","https://openalex.org/W3011120880","https://openalex.org/W3017377990","https://openalex.org/W4214717370","https://openalex.org/W4242798032","https://openalex.org/W6629108313","https://openalex.org/W6629939909","https://openalex.org/W6633783497","https://openalex.org/W6634990565","https://openalex.org/W6676684363","https://openalex.org/W6681106493","https://openalex.org/W6682918131","https://openalex.org/W6684898581","https://openalex.org/W6693390791","https://openalex.org/W6775686901","https://openalex.org/W6776902624"],"related_works":["https://openalex.org/W4239202700","https://openalex.org/W4205569898","https://openalex.org/W146740654","https://openalex.org/W2050153923","https://openalex.org/W3140225428","https://openalex.org/W1538318259","https://openalex.org/W2122027938","https://openalex.org/W2171128163","https://openalex.org/W2230868825","https://openalex.org/W2066913626"],"abstract_inverted_index":{"Machine":[0],"learning":[1,12,18,36,55,58,70,93,100,111],"is":[2,13,37,56,60,80,102,119],"an":[3],"important":[4],"issue":[5],"to":[6,25],"researchers":[7],"for":[8,41,74],"several":[9],"years.":[10],"Reinforcement":[11],"a":[14,31],"type":[15],"of":[16,34,53,109,116],"unsupervised":[17],"which":[19,59],"uses":[20,68],"state-action":[21],"combinations":[22],"and":[23,89,104],"rewards":[24],"interact":[26],"with":[27,72],"the":[28,84,107,114,117],"environment.":[29],"Q-learning":[30,73,118],"further,":[32],"sub-division":[33],"reinforcement":[35],"now-a-days":[38],"well-accepted":[39],"algorithm":[40],"robots":[42],"(machine)":[43],"learning.":[44],"However":[45],"human":[46],"beings":[47],"learn":[48],"in":[49,63],"different":[50],"ways.":[51],"One":[52],"such":[54],"gradual":[57,69],"mostly":[61],"continuous":[62],"nature.":[64],"This":[65],"present":[66],"paper":[67],"combined":[71],"light":[75],"exploration.":[76],"The":[77],"first":[78],"Q-table":[79],"randomly":[81],"generated,":[82],"but":[83,98],"next":[85],"Q-tables":[86],"are":[87],"inter-dependent":[88],"gradually":[90],"refined.":[91],"Initial":[92],"time":[94,101],"may":[95],"be":[96],"high,":[97],"final":[99],"lower":[103],"this":[105,110],"proves":[106],"efficiency":[108],"technique.":[112],"Apart":[113],"convergence":[115],"also":[120],"established.":[121]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
