{"id":"https://openalex.org/W3174239553","doi":"https://doi.org/10.3390/sym13071197","title":"Transition Based Discount Factor for Model Free Algorithms in Reinforcement Learning","display_name":"Transition Based Discount Factor for Model Free Algorithms in Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-02","ids":{"openalex":"https://openalex.org/W3174239553","doi":"https://doi.org/10.3390/sym13071197","mag":"3174239553"},"language":"en","primary_location":{"id":"doi:10.3390/sym13071197","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13071197","pdf_url":"https://www.mdpi.com/2073-8994/13/7/1197/pdf?version=1625458704","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/13/7/1197/pdf?version=1625458704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054150548","display_name":"Abhinav Sharma","orcid":"https://orcid.org/0000-0003-3882-5879"},"institutions":[{"id":"https://openalex.org/I207223250","display_name":"Indian Institute of Information Technology Design and Manufacturing Jabalpur","ror":"https://ror.org/00gmd7q80","country_code":"IN","type":"education","lineage":["https://openalex.org/I207223250"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhinav Sharma","raw_affiliation_strings":["Department of Computer Science, PDPM Indian Institute of Information Technology Jabalpur, Madhya Pradesh 482005, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, PDPM Indian Institute of Information Technology Jabalpur, Madhya Pradesh 482005, India","institution_ids":["https://openalex.org/I207223250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059613803","display_name":"Ruchir Gupta","orcid":"https://orcid.org/0000-0001-9970-3889"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ruchir Gupta","raw_affiliation_strings":["Department of Computer Science, JNU, Delhi 110001, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, JNU, Delhi 110001, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025099834","display_name":"K. Lakshmanan","orcid":null},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]},{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Lakshmanan","raw_affiliation_strings":["Department of Computer Science, IIT (BHU) Varanasi, Uttar Pradesh 221005, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, IIT (BHU) Varanasi, Uttar Pradesh 221005, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025809080","display_name":"Atul Gupta","orcid":"https://orcid.org/0000-0001-5051-5887"},"institutions":[{"id":"https://openalex.org/I207223250","display_name":"Indian Institute of Information Technology Design and Manufacturing Jabalpur","ror":"https://ror.org/00gmd7q80","country_code":"IN","type":"education","lineage":["https://openalex.org/I207223250"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Atul Gupta","raw_affiliation_strings":["Department of Computer Science, PDPM Indian Institute of Information Technology Jabalpur, Madhya Pradesh 482005, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, PDPM Indian Institute of Information Technology Jabalpur, Madhya Pradesh 482005, India","institution_ids":["https://openalex.org/I207223250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059613803"],"corresponding_institution_ids":[],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.28,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62940982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"13","issue":"7","first_page":"1197","last_page":"1197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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":0.9944999814033508,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8708814382553101},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.8509564995765686},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6598920226097107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6402080059051514},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4849986732006073},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.47855979204177856},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.45403194427490234},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45257964730262756},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44079434871673584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44070807099342346},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.43910086154937744},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4156915545463562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34200409054756165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29522931575775146},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.22214758396148682},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.09927436709403992},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0900297462940216}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8708814382553101},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.8509564995765686},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6598920226097107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402080059051514},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4849986732006073},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47855979204177856},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45403194427490234},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45257964730262756},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44079434871673584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44070807099342346},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.43910086154937744},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4156915545463562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34200409054756165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29522931575775146},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.22214758396148682},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.09927436709403992},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0900297462940216},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym13071197","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13071197","pdf_url":"https://www.mdpi.com/2073-8994/13/7/1197/pdf?version=1625458704","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:430d8c43ccfb4a0f82f2a0fafa88bdc6","is_oa":true,"landing_page_url":"https://doaj.org/article/430d8c43ccfb4a0f82f2a0fafa88bdc6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 13, Iss 7, p 1197 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/13/7/1197/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym13071197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym13071197","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13071197","pdf_url":"https://www.mdpi.com/2073-8994/13/7/1197/pdf?version=1625458704","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174239553.pdf","grobid_xml":"https://content.openalex.org/works/W3174239553.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1520148289","https://openalex.org/W1978481500","https://openalex.org/W1983264093","https://openalex.org/W1999172680","https://openalex.org/W2039412751","https://openalex.org/W2055647224","https://openalex.org/W2107726111","https://openalex.org/W2121517924","https://openalex.org/W2124175081","https://openalex.org/W2150339816","https://openalex.org/W2165131254","https://openalex.org/W2514813345","https://openalex.org/W2966362327","https://openalex.org/W2967727187","https://openalex.org/W2972019214","https://openalex.org/W2982316857","https://openalex.org/W2994803162","https://openalex.org/W3000637312","https://openalex.org/W3002044607","https://openalex.org/W3004421451","https://openalex.org/W3012252330","https://openalex.org/W3036160090","https://openalex.org/W3037810159","https://openalex.org/W3080598349","https://openalex.org/W3100789280","https://openalex.org/W3119580723","https://openalex.org/W3123359883","https://openalex.org/W3127561923","https://openalex.org/W3134979610","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W6664299420","https://openalex.org/W6759572487"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W4400868993","https://openalex.org/W2386410636","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W3038962357","https://openalex.org/W2808418668","https://openalex.org/W2100100236","https://openalex.org/W61119710"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"enables":[3],"an":[4,72],"agent":[5],"to":[6,113],"learn":[7,114],"control":[8,108],"policies":[9],"for":[10,64],"achieving":[11],"its":[12],"long-term":[13],"goals.":[14],"One":[15],"key":[16],"parameter":[17],"of":[18,61,90],"RL":[19,111],"algorithms":[20],"is":[21,94],"a":[22,41,122],"discount":[23,43,87],"factor":[24,44,88],"that":[25],"scales":[26],"down":[27],"future":[28],"cost":[29],"in":[30,45,121],"the":[31,59,99,110],"state\u2019s":[32],"current":[33],"value":[34],"estimate.":[35],"This":[36,70],"study":[37],"introduces":[38],"and":[39,52,54,67,102],"analyses":[40],"transition-based":[42],"two":[46],"model-free":[47],"reinforcement":[48],"learning":[49],"algorithms:":[50],"Q-learning":[51],"SARSA,":[53],"shows":[55],"their":[56],"convergence":[57,84],"using":[58],"theory":[60],"stochastic":[62],"approximation":[63],"finite":[65],"state":[66],"action":[68],"spaces.":[69],"causes":[71],"asymmetric":[73],"discounting,":[74],"favouring":[75],"some":[76],"transitions":[77],"over":[78,109],"others,":[79],"which":[80,93],"allows":[81],"(1)":[82],"faster":[83],"than":[85],"constant":[86],"variant":[89],"these":[91],"algorithms,":[92],"demonstrated":[95,120],"by":[96],"experiments":[97],"on":[98],"Taxi":[100],"domain":[101],"MountainCar":[103],"environments;":[104],"(2)":[105],"provides":[106],"better":[107],"agents":[112],"risk-averse":[115],"or":[116],"risk-taking":[117],"policy,":[118],"as":[119],"Cliff":[123],"Walking":[124],"experiment.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
