{"id":"https://openalex.org/W2574558485","doi":"https://doi.org/10.3233/978-1-61499-672-9-1644","title":"A History Tree Heuristic to Generate Better Initiation Sets for Options in Reinforcement Learning","display_name":"A History Tree Heuristic to Generate Better Initiation Sets for Options in Reinforcement Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2574558485","doi":"https://doi.org/10.3233/978-1-61499-672-9-1644","mag":"2574558485"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-672-9-1644","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1644","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5102740538","display_name":"Alper Dem\u0456r","orcid":"https://orcid.org/0000-0003-2646-4850"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Demir Alper","raw_affiliation_strings":["Middle East Technical University, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002885572","display_name":"Erk\u0456n \u00c7\u0456lden","orcid":"https://orcid.org/0000-0003-3451-7326"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"&Ccedil;ilden Erkin","raw_affiliation_strings":["Middle East Technical University, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016249943","display_name":"Faruk Polat","orcid":"https://orcid.org/0000-0003-0509-9153"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Polat Faruk","raw_affiliation_strings":["Middle East Technical University, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102740538"],"corresponding_institution_ids":["https://openalex.org/I201799495"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24775995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1644","last_page":"1645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.8907999992370605,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.8907999992370605,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8553000092506409,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.8075000047683716,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6834918856620789},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.608150064945221},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5381195545196533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5313207507133484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36873307824134827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17772403359413147},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06531620025634766}],"concepts":[{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6834918856620789},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.608150064945221},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5381195545196533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5313207507133484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36873307824134827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17772403359413147},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06531620025634766}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/978-1-61499-672-9-1644","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1644","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:open.metu.edu.tr:11511/35681","is_oa":false,"landing_page_url":"https://hdl.handle.net/11511/35681","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"mag:2574558485","is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ecai/ecai2016.html#DemirCP16","pdf_url":null,"source":{"id":"https://openalex.org/S4306418308","display_name":"European Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"European Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Options":[0],"framework":[1],"is":[2,42],"a":[3],"prominent":[4],"way":[5],"to":[6,24,54],"improve":[7],"learning":[8],"speed":[9],"by":[10],"means":[11],"of":[12,35,39,63,67],"temporally":[13],"extended":[14],"actions,":[15],"called":[16],"options.":[17],"Although":[18],"various":[19],"attempts":[20],"focusing":[21],"on":[22],"how":[23],"derive":[25,55],"high":[26],"quality":[27],"termination":[28],"conditions":[29],"for":[30],"options":[31],"exist,":[32],"the":[33,64],"impact":[34],"initiation":[36,57],"set":[37,58],"generation":[38],"an":[40,50,61],"option":[41],"relatively":[43],"unexplored.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"propose":[49],"effective":[51],"heuristic":[52],"method":[53],"useful":[56],"elements":[59],"via":[60],"analysis":[62],"recent":[65],"history":[66],"events.":[68]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2017-01-26T00:00:00"}
