{"id":"https://openalex.org/W4400995754","doi":"https://doi.org/10.1007/978-3-031-65633-0_9","title":"Regular Reinforcement Learning","display_name":"Regular Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400995754","doi":"https://doi.org/10.1007/978-3-031-65633-0_9"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-65633-0_9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-65633-0_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-65633-0_9.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-65633-0_9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072917760","display_name":"Taylor Dohmen","orcid":"https://orcid.org/0000-0001-5722-4847"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Taylor Dohmen","raw_affiliation_strings":["University of Colorado, Boulder, CO, 80309, USA"],"raw_orcid":"https://orcid.org/0000-0001-5722-4847","affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084221298","display_name":"Mateo Perez","orcid":"https://orcid.org/0000-0003-4220-3212"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mateo Perez","raw_affiliation_strings":["University of Colorado, Boulder, CO, 80309, USA"],"raw_orcid":"https://orcid.org/0000-0003-4220-3212","affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077549627","display_name":"Fabio Somenzi","orcid":"https://orcid.org/0000-0002-2085-2003"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabio Somenzi","raw_affiliation_strings":["University of Colorado, Boulder, CO, 80309, USA"],"raw_orcid":"https://orcid.org/0000-0002-2085-2003","affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020302140","display_name":"Ashutosh Trivedi","orcid":"https://orcid.org/0000-0001-9346-0126"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Trivedi","raw_affiliation_strings":["University of Colorado, Boulder, CO, 80309, USA"],"raw_orcid":"https://orcid.org/0000-0001-9346-0126","affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072917760"],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.498,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82710728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12072","display_name":"Machine Learning and Algorithms","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/T10653","display_name":"Robot Manipulation and Learning","score":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.8378463983535767},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7134436964988708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44897618889808655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378463983535767},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7134436964988708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44897618889808655}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-65633-0_9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-65633-0_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-65633-0_9.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-65633-0_9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-65633-0_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-65633-0_9.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G6332253830","display_name":"SHF: Small: Omega-Regular Objectives for Model-Free Reinforcement Learning","funder_award_id":"2009022","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G842143413","display_name":"CAREER: Reinforcement Learning for Recursive Markov Decision Processes and Beyond","funder_award_id":"2146563","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400995754.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W174941419","https://openalex.org/W569478347","https://openalex.org/W1498256026","https://openalex.org/W1522742464","https://openalex.org/W1526786777","https://openalex.org/W1531120037","https://openalex.org/W1577233792","https://openalex.org/W1650090475","https://openalex.org/W1762311305","https://openalex.org/W1860772589","https://openalex.org/W1861590051","https://openalex.org/W1881102326","https://openalex.org/W1908450151","https://openalex.org/W1971521983","https://openalex.org/W1974086470","https://openalex.org/W1975745970","https://openalex.org/W1982556442","https://openalex.org/W2016770292","https://openalex.org/W2019363670","https://openalex.org/W2047764386","https://openalex.org/W2063247622","https://openalex.org/W2091043802","https://openalex.org/W2101989701","https://openalex.org/W2119296125","https://openalex.org/W2145339207","https://openalex.org/W2145495721","https://openalex.org/W2154229279","https://openalex.org/W2170400507","https://openalex.org/W2257979135","https://openalex.org/W2501206750","https://openalex.org/W2907492528","https://openalex.org/W2963296553","https://openalex.org/W2966174181","https://openalex.org/W2972500268","https://openalex.org/W3035701987","https://openalex.org/W3092156990","https://openalex.org/W3188631122","https://openalex.org/W3197209873","https://openalex.org/W3200738436","https://openalex.org/W3206976301","https://openalex.org/W4205449506","https://openalex.org/W4205728061","https://openalex.org/W4206577354","https://openalex.org/W4283821610","https://openalex.org/W4285602641","https://openalex.org/W4312844584"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"reinforcement":[2,27,52,99,111,128,138,158],"learning,":[3,28,53],"an":[4],"agent":[5],"incrementally":[6],"refines":[7],"a":[8,12,48,107,135,164],"behavioral":[9],"policy":[10],"through":[11,61,160],"series":[13],"of":[14,42,51,57,126,145,155,167],"episodic":[15],"interactions":[16],"with":[17,32],"its":[18,104],"environment.":[19],"This":[20],"process":[21],"can":[22],"be":[23],"characterized":[24],"as":[25,29,83,89,97,106],"explicit":[26,33],"it":[30],"deals":[31],"states":[34,58,82],"and":[35,63,86,102,120,153],"concrete":[36],"transitions.":[37],"Building":[38],"upon":[39],"the":[40,81,124,143,151],"concept":[41],"symbolic":[43,49,108],"model":[44,74],"checking,":[45,75],"we":[46,76,114,133],"propose":[47],"variant":[50],"in":[54,123],"which":[55],"sets":[56],"are":[59,65],"represented":[60,66],"predicates":[62],"transitions":[64],"by":[67,142],"predicate":[68,90],"transformers.":[69],"Drawing":[70],"inspiration":[71],"from":[72],"regular":[73,78,98,127,137,157],"choose":[77],"languages":[79],"over":[80],"our":[84],"predicates,":[85],"rational":[87],"transductions":[88],"transformations.":[91],"We":[92,149],"refer":[93],"to":[94,110],"this":[95],"framework":[96],"learning":[100,139,159],",":[101],"study":[103],"utility":[105],"approach":[109],"learning.":[112,129],"Theoretically,":[113],"establish":[115],"results":[116],"around":[117],"decidability,":[118],"approximability,":[119],"efficient":[121],"learnability":[122],"context":[125],"Towards":[130],"practical":[131],"applications,":[132],"develop":[134],"deep":[136],"algorithm,":[140],"enabled":[141],"use":[144],"graph":[146],"neural":[147],"networks.":[148],"showcase":[150],"applicability":[152],"effectiveness":[154],"(deep)":[156],"empirical":[161],"evaluation":[162],"on":[163],"diverse":[165],"set":[166],"case":[168],"studies.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}