{"id":"https://openalex.org/W2997729838","doi":"https://doi.org/10.1109/icccnt45670.2019.8944912","title":"An Optimal Transfer of Knowledge in Reinforcement Learning through Greedy Approach","display_name":"An Optimal Transfer of Knowledge in Reinforcement Learning through Greedy Approach","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2997729838","doi":"https://doi.org/10.1109/icccnt45670.2019.8944912","mag":"2997729838"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt45670.2019.8944912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt45670.2019.8944912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015327224","display_name":"Deepika Kumari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepika Kumari","raw_affiliation_strings":["Department of I.T., REC Ambedkar Nagar, UP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of I.T., REC Ambedkar Nagar, UP, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008850404","display_name":"Mahima Chaudhary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahima Chaudhary","raw_affiliation_strings":["Department of I.T., REC Ambedkar Nagar, UP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of I.T., REC Ambedkar Nagar, UP, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101761305","display_name":"Ashish Kumar Mishra","orcid":"https://orcid.org/0000-0002-7532-5585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Kumar Mishra","raw_affiliation_strings":["Department of I.T., REC Ambedkar Nagar, UP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of I.T., REC Ambedkar Nagar, UP, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44159889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9939000010490417,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9728999733924866,"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/initialization","display_name":"Initialization","score":0.8458219766616821},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8099333047866821},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7360478043556213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7061981558799744},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5665303468704224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631935596466064},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.540904700756073},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5024194717407227},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4930512607097626},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4515494406223297},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42599767446517944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21370166540145874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18221953511238098},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11928963661193848}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8458219766616821},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8099333047866821},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7360478043556213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7061981558799744},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5665303468704224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631935596466064},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.540904700756073},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5024194717407227},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4930512607097626},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4515494406223297},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42599767446517944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21370166540145874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18221953511238098},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11928963661193848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/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/icccnt45670.2019.8944912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt45670.2019.8944912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","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":17,"referenced_works":["https://openalex.org/W1533597678","https://openalex.org/W1550698229","https://openalex.org/W1570448133","https://openalex.org/W1600437712","https://openalex.org/W2041367235","https://openalex.org/W2109910161","https://openalex.org/W2113913482","https://openalex.org/W2114580749","https://openalex.org/W2133040789","https://openalex.org/W2741594138","https://openalex.org/W2782656435","https://openalex.org/W2885671219","https://openalex.org/W2890735789","https://openalex.org/W2902334345","https://openalex.org/W3020831056","https://openalex.org/W3139377883","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4386121542"],"abstract_inverted_index":{"Transfer":[0],"Learning":[1,7],"has":[2,75,110,160],"been":[3,76,111,161],"used":[4,112],"in":[5,66,87,113],"Reinforcement":[6,91],"methods":[8],"by":[9,103],"integrating":[10],"information":[11,34],"from":[12,35],"preceding":[13],"task.":[14,40],"Although,":[15],"these":[16,164],"algorithms":[17],"generally":[18],"have":[19,45],"to":[20,38,56,78,124,166],"be":[21],"assigned":[22],"either":[23],"a":[24],"complete":[25],"prototype":[26],"of":[27,33,48,90,139],"the":[28,46,58,88,94,118,129,132,156],"task":[29,37],"or":[30,69],"direct":[31],"mapping":[32],"input":[36],"output":[39],"The":[41,107],"agent":[42],"may":[43],"not":[44],"knowledge":[47,119],"such":[49],"complex":[50],"information.":[51],"However,":[52],"it":[53],"is":[54],"able":[55],"examine":[57],"resemblance":[59],"between":[60],"two":[61],"tasks":[62],"which":[63],"are":[64,135],"similar":[65],"taking":[67],"action":[68],"approach.":[70,106],"In":[71,128,155],"this":[72],"paper":[73],"efforts":[74],"made":[77],"solve":[79],"mountain":[80,122,126],"car":[81,123],"problem":[82,85],"(a":[83],"famous":[84],"domain":[86],"area":[89],"Learning)":[92],"using":[93,104],"SARSA":[95],"(\u03bb)":[96],"[10]":[97],"algorithm":[98],"and":[99,151],"MASTER":[100],"[3]":[101],"method":[102],"greedy":[105,108,158],"approach":[109,159],"applying":[114],"parameters":[115,140,165],"for":[116],"transferring":[117],"within":[120],"2-dimensional":[121],"3-dimensional":[125],"car.":[127],"existing":[130],"techniques":[131],"best":[133],"results":[134],"obtained":[136],"with":[137,147,163],"use":[138],"like":[141],"epsilon":[142],"decay":[143,149],"factor,":[144],"eligibility":[145],"traces":[146],"greater":[148],"factor":[150],"positive":[152],"weight":[153],"initialization.":[154],"article,":[157],"applied":[162],"get":[167],"optimal":[168],"results.":[169]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}