{"id":"https://openalex.org/W2182103321","doi":"https://doi.org/10.1007/978-3-642-23887-1_89","title":"Principled Methods for Biasing Reinforcement Learning Agents","display_name":"Principled Methods for Biasing Reinforcement Learning Agents","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2182103321","doi":"https://doi.org/10.1007/978-3-642-23887-1_89","mag":"2182103321"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-23887-1_89","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-23887-1_89","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/A5100685911","display_name":"Zhi Li","orcid":"https://orcid.org/0000-0002-4869-6778"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101653558","display_name":"Kun Hu","orcid":"https://orcid.org/0000-0003-1178-9652"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Hu","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112107398","display_name":"Zengrong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengrong Liu","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100966002","display_name":"Xueli Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueli Yu","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, 79 Yingze West Street, Taiyuan City, Shanxi Province, China","institution_ids":["https://openalex.org/I9086337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9086337"],"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":0.23646879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"703","last_page":"709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9908000230789185,"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":0.9839000105857849,"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":0.8755894303321838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8374756574630737},{"id":"https://openalex.org/keywords/slowness","display_name":"Slowness","score":0.8051969408988953},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6571050882339478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577916502952576},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5456224083900452},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41297629475593567}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8755894303321838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374756574630737},{"id":"https://openalex.org/C11940443","wikidata":"https://www.wikidata.org/wiki/Q16965645","display_name":"Slowness","level":2,"score":0.8051969408988953},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6571050882339478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577916502952576},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5456224083900452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41297629475593567},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-23887-1_89","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-23887-1_89","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W89091142","https://openalex.org/W181569489","https://openalex.org/W354832773","https://openalex.org/W1515851193","https://openalex.org/W1557517019","https://openalex.org/W1610678877","https://openalex.org/W2121863487","https://openalex.org/W2123354780","https://openalex.org/W2125946670","https://openalex.org/W2164419340","https://openalex.org/W3011120880","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W3103461978","https://openalex.org/W2356299150","https://openalex.org/W4378230892","https://openalex.org/W2003964906","https://openalex.org/W4391981100","https://openalex.org/W4389273484","https://openalex.org/W2144966994","https://openalex.org/W3017010751","https://openalex.org/W2168615451","https://openalex.org/W1984459742"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
