{"id":"https://openalex.org/W2882982657","doi":"https://doi.org/10.1007/978-3-319-97304-3_7","title":"Adaptively Shaping Reinforcement Learning Agents via Human Reward","display_name":"Adaptively Shaping Reinforcement Learning Agents via Human Reward","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2882982657","doi":"https://doi.org/10.1007/978-3-319-97304-3_7","mag":"2882982657"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-97304-3_7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-97304-3_7","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":"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/A5074681163","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0002-4371-3663"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Yu","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433001","display_name":"Dongxu Wang","orcid":"https://orcid.org/0000-0002-4427-4412"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongxu Wang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619771","display_name":"Tianpei Yang","orcid":"https://orcid.org/0000-0002-5497-7146"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianpei Yang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101556242","display_name":"Wenxuan Zhu","orcid":"https://orcid.org/0000-0002-4981-9258"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348344","display_name":"Yuchen Li","orcid":"https://orcid.org/0000-0001-9646-291X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Li","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091010251","display_name":"Hongwei Ge","orcid":"https://orcid.org/0000-0002-8937-1515"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Ge","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016595900","display_name":"Jiankang Ren","orcid":"https://orcid.org/0000-0001-6289-1513"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankang Ren","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5074681163"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.8156,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75990209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9948999881744385,"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":0.9948999881744385,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9083999991416931,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9255243539810181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8156182765960693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6511105298995972},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5118154883384705},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4685944616794586},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46680572628974915},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4581848680973053},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2467433512210846},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.13951894640922546}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9255243539810181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156182765960693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511105298995972},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5118154883384705},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4685944616794586},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46680572628974915},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4581848680973053},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2467433512210846},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.13951894640922546},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-97304-3_7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-97304-3_7","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W946252087","https://openalex.org/W1453801241","https://openalex.org/W1529399279","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1981158530","https://openalex.org/W1991284037","https://openalex.org/W2031727428","https://openalex.org/W2049538695","https://openalex.org/W2054339854","https://openalex.org/W2098441518","https://openalex.org/W2107112577","https://openalex.org/W2110064869","https://openalex.org/W2116157560","https://openalex.org/W2121863487","https://openalex.org/W2137375617","https://openalex.org/W2151382427","https://openalex.org/W2165792602","https://openalex.org/W2173248099","https://openalex.org/W2189058185","https://openalex.org/W2290053245","https://openalex.org/W2294422333","https://openalex.org/W2397581010","https://openalex.org/W2491675558","https://openalex.org/W2575705757","https://openalex.org/W2604283518","https://openalex.org/W2949608212","https://openalex.org/W2962676505","https://openalex.org/W3099324303","https://openalex.org/W4214717370","https://openalex.org/W6634537889","https://openalex.org/W6731858228"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2930863966","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2126211886","https://openalex.org/W2367922714","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W3119422923"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
