{"id":"https://openalex.org/W3042737320","doi":"https://doi.org/10.1162/isal_a_00338","title":"Reinforcement learning beyond the Bellman equation: Exploring critic objectives using evolution","display_name":"Reinforcement learning beyond the Bellman equation: Exploring critic objectives using evolution","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3042737320","doi":"https://doi.org/10.1162/isal_a_00338","mag":"3042737320"},"language":"en","primary_location":{"id":"doi:10.1162/isal_a_00338","is_oa":true,"landing_page_url":"https://doi.org/10.1162/isal_a_00338","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/isal_a_00338","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2020 Conference on Artificial Life","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/isal_a_00338","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062214130","display_name":"Abe Leite","orcid":"https://orcid.org/0000-0003-1115-3646"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abe Leite","raw_affiliation_strings":["Cognitive Science Program, Indiana University Bloomington Corresponding email:"],"affiliations":[{"raw_affiliation_string":"Cognitive Science Program, Indiana University Bloomington Corresponding email:","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007298239","display_name":"Madhavun Candadai","orcid":"https://orcid.org/0000-0002-9254-8641"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madhavun Candadai","raw_affiliation_strings":["Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington"],"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075822106","display_name":"Eduardo J. Izquierdo","orcid":"https://orcid.org/0000-0002-2008-290X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduardo J. Izquierdo","raw_affiliation_strings":["Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington"],"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062214130"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75712296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9829999804496765,"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":0.9829999804496765,"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":0.9624000191688538,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9301000237464905,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.90900719165802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6121190190315247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5184109210968018},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4654003083705902},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.45256713032722473},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3290172815322876},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1520569622516632}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.90900719165802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6121190190315247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184109210968018},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4654003083705902},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.45256713032722473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3290172815322876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1520569622516632},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/isal_a_00338","is_oa":true,"landing_page_url":"https://doi.org/10.1162/isal_a_00338","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/isal_a_00338","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2020 Conference on Artificial Life","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1162/isal_a_00338","is_oa":true,"landing_page_url":"https://doi.org/10.1162/isal_a_00338","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/isal_a_00338","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2020 Conference on Artificial Life","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3042737320.pdf","grobid_xml":"https://content.openalex.org/works/W3042737320.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W73189514","https://openalex.org/W1757796397","https://openalex.org/W2027475699","https://openalex.org/W2046376809","https://openalex.org/W2056653303","https://openalex.org/W2078506364","https://openalex.org/W2097571405","https://openalex.org/W2121863487","https://openalex.org/W2171658832","https://openalex.org/W2173248099","https://openalex.org/W2580175322","https://openalex.org/W2583761661","https://openalex.org/W2726772824","https://openalex.org/W2766447205","https://openalex.org/W2778749116","https://openalex.org/W2787387965","https://openalex.org/W2906697496","https://openalex.org/W2946004135","https://openalex.org/W2998349125","https://openalex.org/W3130385304"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Living":[0],"organisms":[1],"learn":[2],"on":[3],"multiple":[4],"time":[5],"scales:":[6],"evolutionary":[7],"as":[8,10],"well":[9],"individual-lifetime":[11],"learning.":[12],"These":[13],"two":[14],"learning":[15],"modes":[16],"are":[17],"complementary:":[18],"the":[19],"innate":[20],"phenotypes":[21],"developed":[22],"through":[23],"evolution":[24],"s...":[25]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}