{"id":"https://openalex.org/W1496685878","doi":"https://doi.org/10.1007/978-3-642-15880-3_36","title":"Feature Selection for Reinforcement Learning: Evaluating Implicit State-Reward Dependency via Conditional Mutual Information","display_name":"Feature Selection for Reinforcement Learning: Evaluating Implicit State-Reward Dependency via Conditional Mutual Information","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1496685878","doi":"https://doi.org/10.1007/978-3-642-15880-3_36","mag":"1496685878"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-15880-3_36","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-15880-3_36","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-642-15880-3_36.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":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":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-642-15880-3_36.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073076975","display_name":"Hirotaka Hachiya","orcid":"https://orcid.org/0000-0003-3748-4101"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hirotaka Hachiya","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, 152-8552, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, 152-8552, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073076975"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.1057,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92215844,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.991599977016449,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9897000193595886,"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/mutual-information","display_name":"Mutual information","score":0.8039077520370483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7881776094436646},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7687736749649048},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6741814017295837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6222909688949585},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5864266157150269},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5698772072792053},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48147669434547424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4678533673286438},{"id":"https://openalex.org/keywords/conditional-mutual-information","display_name":"Conditional mutual information","score":0.42136022448539734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33454954624176025}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.8039077520370483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881776094436646},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7687736749649048},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6741814017295837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6222909688949585},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5864266157150269},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5698772072792053},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48147669434547424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4678533673286438},{"id":"https://openalex.org/C124805900","wikidata":"https://www.wikidata.org/wiki/Q5159269","display_name":"Conditional mutual information","level":3,"score":0.42136022448539734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33454954624176025},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-15880-3_36","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-15880-3_36","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-642-15880-3_36.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":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:CiteSeerX.psu:10.1.1.386.2141","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.2141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sugiyama-www.cs.titech.ac.jp/~sugi/2010/ECML-PKDD2010.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/978-3-642-15880-3_36","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-15880-3_36","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-642-15880-3_36.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":null,"license_id":null,"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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1496685878.pdf","grobid_xml":"https://content.openalex.org/works/W1496685878.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1607198972","https://openalex.org/W1981276685","https://openalex.org/W2011233848","https://openalex.org/W2072460512","https://openalex.org/W2080039641","https://openalex.org/W2083505311","https://openalex.org/W2101267652","https://openalex.org/W2102689555","https://openalex.org/W2103996345","https://openalex.org/W2117423905","https://openalex.org/W2119479037","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2123157758","https://openalex.org/W2123168458","https://openalex.org/W2123979492","https://openalex.org/W2130801532","https://openalex.org/W2138326839","https://openalex.org/W2144935315","https://openalex.org/W2148277778","https://openalex.org/W2148603752","https://openalex.org/W2595697910","https://openalex.org/W2999905431","https://openalex.org/W3098474648","https://openalex.org/W3140968660","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W6621238143"],"related_works":["https://openalex.org/W4205619203","https://openalex.org/W2997083166","https://openalex.org/W2086424613","https://openalex.org/W3135541457","https://openalex.org/W2053515329","https://openalex.org/W3037363193","https://openalex.org/W4313429060","https://openalex.org/W2386078281","https://openalex.org/W2533731304","https://openalex.org/W1770458422"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}