{"id":"https://openalex.org/W2548807688","doi":"https://doi.org/10.1109/dsaa.2014.7058045","title":"Minimizing expected loss for risk-avoiding reinforcement learning","display_name":"Minimizing expected loss for risk-avoiding reinforcement learning","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2548807688","doi":"https://doi.org/10.1109/dsaa.2014.7058045","mag":"2548807688"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa.2014.7058045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2014.7058045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"},"type":"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/A5113519015","display_name":"Jung-Jung Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I96323854","display_name":"National Yang Ming Chiao Tung University","ror":null,"country_code":"TW","type":null,"lineage":["https://openalex.org/I96323854"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jung-Jung Yeh","raw_affiliation_strings":["National Taiwan University","[National Taiwan University Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I96323854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046477105","display_name":"Tsung-Ting Kuo","orcid":"https://orcid.org/0000-0002-8728-4477"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I96323854","display_name":"National Yang Ming Chiao Tung University","ror":null,"country_code":"TW","type":null,"lineage":["https://openalex.org/I96323854"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Ting Kuo","raw_affiliation_strings":["National Taiwan University","[National Taiwan University Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I96323854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055644612","display_name":"William Chen","orcid":"https://orcid.org/0000-0001-8924-5853"},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"William Chen","raw_affiliation_strings":["Institute for Information Industry Taipei, Taiwan","Institute for Information Industry,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Industry Taipei, Taiwan","institution_ids":["https://openalex.org/I3141939062"]},{"raw_affiliation_string":"Institute for Information Industry,Taipei,Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087480257","display_name":"Shou-De Lin","orcid":"https://orcid.org/0000-0001-9970-1250"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I96323854","display_name":"National Yang Ming Chiao Tung University","ror":null,"country_code":"TW","type":null,"lineage":["https://openalex.org/I96323854"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shou-De Lin","raw_affiliation_strings":["National Taiwan University","[National Taiwan University Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I96323854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.24236274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9986000061035156,"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":0.9986000061035156,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9147173166275024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060613632202148},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5295392274856567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47674569487571716},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.47048118710517883},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4200165867805481},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4182392656803131},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3277119994163513},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10406380891799927},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06309601664543152}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9147173166275024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060613632202148},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5295392274856567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47674569487571716},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.47048118710517883},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4200165867805481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4182392656803131},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3277119994163513},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10406380891799927},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06309601664543152},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa.2014.7058045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2014.7058045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318019","display_name":"Asian Office of Aerospace Research and Development","ror":null},{"id":"https://openalex.org/F4320336958","display_name":"Institute for Information Industry, Ministry of Science and Technology, Taiwan","ror":"https://ror.org/01d8kr740"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W9583197","https://openalex.org/W134786152","https://openalex.org/W1509702171","https://openalex.org/W1551275368","https://openalex.org/W1558348055","https://openalex.org/W1585575029","https://openalex.org/W1984151138","https://openalex.org/W2057510529","https://openalex.org/W2066809750","https://openalex.org/W2085317472","https://openalex.org/W2101075098","https://openalex.org/W2104269165","https://openalex.org/W2121863487","https://openalex.org/W2125069914","https://openalex.org/W2130100150","https://openalex.org/W2136202932","https://openalex.org/W2166362129","https://openalex.org/W2312609093","https://openalex.org/W2341171179","https://openalex.org/W3011120880","https://openalex.org/W3106238320","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W6632850048","https://openalex.org/W6633575394","https://openalex.org/W6680080562","https://openalex.org/W6704298589","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2041126907","https://openalex.org/W2130711276"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"the":[3,57,76,81],"design":[4,45],"of":[5,26,36,65,84,98],"a":[6,14,34,46,51],"reinforcement":[7,52],"learning":[8,53,88],"(RL)":[9],"agent":[10,54],"that":[11,49,75],"can":[12],"strike":[13],"balance":[15,58],"between":[16,59],"return":[17],"and":[18,31,61,70,90],"risk.":[19],"First,":[20],"we":[21],"discuss":[22],"several":[23],"favorable":[24],"properties":[25,83],"an":[27,85],"RL":[28],"risk":[29,37,60,78,87],"model,":[30,89],"then":[32],"propose":[33],"definition":[35],"based":[38],"on":[39,67],"expected":[40],"negative":[41],"rewards.":[42],"We":[43],"also":[44,91],"Q-decomposition-based":[47],"framework":[48],"allows":[50],"to":[55],"control":[56],"profit.":[62],"The":[63],"results":[64],"experiments":[66],"both":[68],"artificial":[69],"real-world":[71],"stock":[72],"datasets":[73],"demonstrate":[74],"proposed":[77],"model":[79],"satisfies":[80],"beneficial":[82],"RL-based":[86],"significantly":[92],"outperforms":[93],"other":[94],"approaches":[95],"in":[96],"terms":[97],"avoiding":[99],"risks.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}