{"id":"https://openalex.org/W4388468296","doi":"https://doi.org/10.1007/978-3-031-47994-6_26","title":"Q-Learning: Solutions for Grid World Problem with Forward and Backward Reward Propagations","display_name":"Q-Learning: Solutions for Grid World Problem with Forward and Backward Reward Propagations","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388468296","doi":"https://doi.org/10.1007/978-3-031-47994-6_26"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-47994-6_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-47994-6_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5113041929","display_name":"Snobin Antony","orcid":null},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Snobin Antony","raw_affiliation_strings":["School of Computing, Ulster University, Belfast, Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Belfast, Northern Ireland","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101264668","display_name":"Raghi Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Raghi Roy","raw_affiliation_strings":["School of Computing, Ulster University, Belfast, Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Belfast, Northern Ireland","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027797605","display_name":"Yaxin Bi","orcid":"https://orcid.org/0000-0002-0979-4084"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yaxin Bi","raw_affiliation_strings":["School of Computing, Ulster University, Belfast, Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Belfast, Northern Ireland","institution_ids":["https://openalex.org/I138801177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113041929"],"corresponding_institution_ids":["https://openalex.org/I138801177"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9889000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8706486225128174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8479073643684387},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8231717348098755},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7812711000442505},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6777102947235107},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6542538404464722},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48686662316322327},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4754447937011719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4557177722454071},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.442929208278656},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3889378011226654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3296683728694916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08725619316101074}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8706486225128174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479073643684387},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8231717348098755},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7812711000442505},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6777102947235107},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6542538404464722},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48686662316322327},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4754447937011719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4557177722454071},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.442929208278656},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3889378011226654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3296683728694916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08725619316101074},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.1007/978-3-031-47994-6_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-47994-6_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2038880985","https://openalex.org/W2126291936","https://openalex.org/W2165713838","https://openalex.org/W2574473771","https://openalex.org/W3099098707","https://openalex.org/W3128125614"],"related_works":["https://openalex.org/W4281847915","https://openalex.org/W2911962197","https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W1626977535","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W1985560493"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}