{"id":"https://openalex.org/W4400348486","doi":"https://doi.org/10.32473/flairs.37.1.135591","title":"Reinforcement Learning Agents with Generalizing Behavior","display_name":"Reinforcement Learning Agents with Generalizing Behavior","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4400348486","doi":"https://doi.org/10.32473/flairs.37.1.135591"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.32473/flairs.37.1.135591","pdf_url":null,"source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","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/A5052235241","display_name":"Sarah Kitchen","orcid":"https://orcid.org/0009-0008-7244-9049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarah Kitchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047771767","display_name":"Reid W. Sawtell","orcid":"https://orcid.org/0009-0003-3291-7446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reid Sawtell","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100020908","display_name":"Anthony Chavez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anthony Chavez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083843489","display_name":"Timothy Aris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Aris","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":78},"biblio":{"volume":"37","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.3871,"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"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.3871,"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":[],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.8460572},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6358184},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3815645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32863674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20216587},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1780523}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.32473/flairs.37.1.135591","pdf_url":null,"source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W4310083477","https://openalex.org/W2920061524","https://openalex.org/W2748952813","https://openalex.org/W2328553770","https://openalex.org/W2145821588","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2038908348","https://openalex.org/W1977959518"],"abstract_inverted_index":{"We":[0,35],"explore":[1],"the":[2,15,66,75],"generality":[3],"of":[4,17,63,69,77],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"agents":[8],"on":[9,39,59],"unseen":[10],"environment":[11,26],"configurations":[12],"by":[13],"analyzing":[14],"behavior":[16],"an":[18],"agent":[19],"tasked":[20],"with":[21],"traversing":[22],"a":[23,28,32,40,60,71],"graph":[24],"based":[25],"from":[27],"starting":[29],"position":[30],"to":[31,45,55],"goal":[33],"position.":[34],"find":[36],"that":[37,50],"training":[38,58,79],"single":[41],"task":[42],"is":[43],"likely":[44],"result":[46],"in":[47],"inflexible":[48],"policies":[49],"do":[51],"not":[52],"respond":[53],"well":[54],"change.":[56],"Instead,":[57],"wide":[61],"variety":[62],"scenarios":[64],"offers":[65],"best":[67],"chance":[68],"developing":[70],"flexible":[72],"policy,":[73],"at":[74],"expense":[76],"increased":[78],"difficulty.":[80]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4400348486","counts_by_year":[],"updated_date":"2025-04-07T05:21:28.958516","created_date":"2024-07-06"}