{"id":"https://openalex.org/W3016524197","doi":"https://doi.org/10.1007/978-3-030-47358-7_6","title":"Reinforcement Learning in a Physics-Inspired Semi-Markov Environment","display_name":"Reinforcement Learning in a Physics-Inspired Semi-Markov Environment","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3016524197","doi":"https://doi.org/10.1007/978-3-030-47358-7_6","mag":"3016524197"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-47358-7_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-47358-7_6","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.07333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033365772","display_name":"Colin Bellinger","orcid":"https://orcid.org/0000-0002-3567-7834"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Colin Bellinger","raw_affiliation_strings":["National Research Council of Canada, Ottawa, Canada","National Research Council of Canada Ottawa. Canada"],"affiliations":[{"raw_affiliation_string":"National Research Council of Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I4210159778"]},{"raw_affiliation_string":"National Research Council of Canada Ottawa. Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297042","display_name":"Rory Coles","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rory Coles","raw_affiliation_strings":["University of Victoria, Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"University of Victoria, Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064795613","display_name":"Mark Crowley","orcid":"https://orcid.org/0000-0003-3921-4762"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mark Crowley","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada","University of Waterloo. Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo. Waterloo, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029833367","display_name":"Isaac Tamblyn","orcid":"https://orcid.org/0000-0002-8146-6667"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Isaac Tamblyn","raw_affiliation_strings":["National Research Council of Canada, Ottawa, Canada","Vector Institute for Artificial Intelligence, Toronto, Canada","National Research Council of Canada Ottawa. Canada"],"affiliations":[{"raw_affiliation_string":"National Research Council of Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I4210159778"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"National Research Council of Canada Ottawa. Canada","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033365772"],"corresponding_institution_ids":["https://openalex.org/I4210159778"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08811641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9754999876022339,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9745000004768372,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.828468918800354},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7716346979141235},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.7268753051757812},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.70967036485672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962534785270691},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5609256625175476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5438622832298279},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5260405540466309},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43756696581840515},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.43001365661621094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3805316686630249},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3210890293121338},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2706822156906128},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12390923500061035}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.828468918800354},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7716346979141235},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.7268753051757812},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.70967036485672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962534785270691},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5609256625175476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5438622832298279},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5260405540466309},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43756696581840515},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.43001365661621094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3805316686630249},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3210890293121338},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2706822156906128},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12390923500061035},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/978-3-030-47358-7_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-47358-7_6","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"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:3f553680-18d6-429c-8fc0-4c3ae973c0aa","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=3f553680-18d6-429c-8fc0-4c3ae973c0aa","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:arXiv.org:2004.07333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.07333","pdf_url":"https://arxiv.org/pdf/2004.07333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3016524197","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2004.07333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.07333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.07333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.07333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.07333","pdf_url":"https://arxiv.org/pdf/2004.07333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1491843047","https://openalex.org/W1757796397","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2809157146","https://openalex.org/W2902929788","https://openalex.org/W2909240409","https://openalex.org/W2962938178","https://openalex.org/W2964001908","https://openalex.org/W2973997324","https://openalex.org/W3011120880","https://openalex.org/W3024236153","https://openalex.org/W3099189920","https://openalex.org/W3104956673","https://openalex.org/W6637967152","https://openalex.org/W6740801417","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3029842769","https://openalex.org/W2074379389","https://openalex.org/W2968286045","https://openalex.org/W1541084404","https://openalex.org/W2953146157","https://openalex.org/W52153049","https://openalex.org/W2154623234","https://openalex.org/W3182829817","https://openalex.org/W2573099472","https://openalex.org/W2381909226","https://openalex.org/W2168024904","https://openalex.org/W1539054658","https://openalex.org/W2183018497","https://openalex.org/W3110191413","https://openalex.org/W2970483889","https://openalex.org/W2475033241","https://openalex.org/W3035880215","https://openalex.org/W2997053847","https://openalex.org/W3208638985","https://openalex.org/W1985119984"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
