{"id":"https://openalex.org/W2404616412","doi":"https://doi.org/10.3233/978-1-61499-419-0-1021","title":"Off-Policy Shaping Ensembles in Reinforcement Learning","display_name":"Off-Policy Shaping Ensembles in Reinforcement Learning","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2404616412","doi":"https://doi.org/10.3233/978-1-61499-419-0-1021","mag":"2404616412"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-419-0-1021","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-419-0-1021","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/978-1-61499-419-0-1021","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014267939","display_name":"Anna Harutyunyan","orcid":"https://orcid.org/0000-0002-5418-113X"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Harutyunyan Anna","raw_affiliation_strings":["AI Lab, Vrije Universiteit Brussel, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"AI Lab, Vrije Universiteit Brussel, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084002137","display_name":"Tim Brys","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brys Tim","raw_affiliation_strings":["AI Lab, Vrije Universiteit Brussel, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"AI Lab, Vrije Universiteit Brussel, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062896285","display_name":"Peter Vrancx","orcid":"https://orcid.org/0000-0002-9876-3684"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Vrancx Peter","raw_affiliation_strings":["AI Lab, Vrije Universiteit Brussel, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"AI Lab, Vrije Universiteit Brussel, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Now&eacute; Ann","raw_affiliation_strings":["AI Lab, Vrije Universiteit Brussel, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"AI Lab, Vrije Universiteit Brussel, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014267939"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":1.3849,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83169097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9914000034332275,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7017034888267517},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5663921236991882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39448317885398865},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2981198728084564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26312077045440674},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10324752330780029}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7017034888267517},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5663921236991882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39448317885398865},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2981198728084564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26312077045440674},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10324752330780029}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-419-0-1021","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-419-0-1021","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/978-1-61499-419-0-1021","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-419-0-1021","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W168823656","https://openalex.org/W1515851193","https://openalex.org/W1543837481","https://openalex.org/W1646707810","https://openalex.org/W1777239053","https://openalex.org/W2002305926","https://openalex.org/W2043806097","https://openalex.org/W2121863487","https://openalex.org/W2128073546","https://openalex.org/W2128786740","https://openalex.org/W2132622533","https://openalex.org/W2135293965","https://openalex.org/W2151613683","https://openalex.org/W2949992425"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3],"propose":[4],"learning":[5],"an":[6],"ensemble":[7],"of":[8],"policies":[9],"related":[10],"through":[11],"potential-based":[12],"shaping":[13],"rewards":[14],"via":[15],"the":[16],"off-policy":[17],"Horde":[18],"framework.":[19]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
