{"id":"https://openalex.org/W3035464578","doi":"https://doi.org/10.24963/ijcai.2020/627","title":"An End-to-End Optimal Trade Execution Framework based on Proximal Policy Optimization","display_name":"An End-to-End Optimal Trade Execution Framework based on Proximal Policy Optimization","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035464578","doi":"https://doi.org/10.24963/ijcai.2020/627","mag":"3035464578"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/627","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/627","pdf_url":"https://www.ijcai.org/proceedings/2020/0627.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0627.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101995168","display_name":"Siyu Lin","orcid":"https://orcid.org/0000-0001-8726-943X"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siyu Lin","raw_affiliation_strings":["University of Virginia, Charlottesville, VA","University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056670558","display_name":"Peter A. Beling","orcid":"https://orcid.org/0000-0003-2196-6982"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter A. Beling","raw_affiliation_strings":["University of Virginia, Charlottesville, VA","University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101995168"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":2.6067,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91654509,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4548","last_page":"4554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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/T11182","display_name":"Auction Theory and Applications","score":0.9713000059127808,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9702000021934509,"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/computer-science","display_name":"Computer science","score":0.7872065305709839},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.724033772945404},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6748635768890381},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6587644815444946},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6046337485313416},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5983884930610657},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4567256569862366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3974943161010742},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34574460983276367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872065305709839},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.724033772945404},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6748635768890381},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6587644815444946},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6046337485313416},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5983884930610657},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4567256569862366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974943161010742},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34574460983276367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/627","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/627","pdf_url":"https://www.ijcai.org/proceedings/2020/0627.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/627","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/627","pdf_url":"https://www.ijcai.org/proceedings/2020/0627.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035464578.pdf","grobid_xml":"https://content.openalex.org/works/W3035464578.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1509716043","https://openalex.org/W1988270113","https://openalex.org/W2001770658","https://openalex.org/W2003205995","https://openalex.org/W2064675550","https://openalex.org/W2082211306","https://openalex.org/W2129432447","https://openalex.org/W2145339207","https://openalex.org/W2736601468","https://openalex.org/W2883265831","https://openalex.org/W2904489222","https://openalex.org/W4239016955","https://openalex.org/W4298857966","https://openalex.org/W6630362020","https://openalex.org/W6647666552","https://openalex.org/W6650530360"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2151749779","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W3179968364"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,94],"propose":[4],"an":[5,113],"end-to-end":[6],"adaptive":[7],"framework":[8,64,154],"for":[9,25],"optimal":[10],"trade":[11,67],"execution":[12,68],"based":[13,33,70],"on":[14,34,71,178],"Proximal":[15],"Policy":[16],"Optimization":[17],"(PPO).":[18],"We":[19],"use":[20,95],"two":[21,35],"methods":[22],"to":[23],"account":[24],"the":[26,30,52,102,107,120,142,157,181],"time":[27],"dependencies":[28],"in":[29,90,146,185],"market":[31],"data":[32],"different":[36],"neural":[37],"network":[38],"architecture:":[39],"1)":[40],"Long":[41],"short-term":[42],"memory":[43],"(LSTM)":[44],"networks,":[45],"2)":[46],"Fully-connected":[47],"networks":[48],"(FCN)":[49],"by":[50],"stacking":[51],"most":[53,179],"recent":[54],"limit":[55,73],"orderbook":[56],"(LOB)":[57,76],"information":[58,77],"as":[59,79,89,112,164,169,171],"model":[60],"inputs.":[61],"The":[62,133,152],"proposed":[63,153],"can":[65],"make":[66],"decisions":[69],"level-2":[72],"order":[74],"book":[75],"such":[78,163],"bid/ask":[80],"prices":[81],"and":[82,141,150,167],"volumes":[83],"directly":[84],"without":[85],"manually":[86],"designed":[87],"attributes":[88],"previous":[91],"research.":[92],"Furthermore,":[93],"a":[96,129],"sparse":[97],"reward":[98,104,131,144],"function,":[99],"which":[100],"gives":[101],"agent":[103],"signals":[105],"at":[106],"end":[108],"of":[109,115,148,180],"each":[110],"episode":[111],"indicator":[114],"its":[116],"relative":[117],"performances":[118],"against":[119],"baseline":[121,161],"model,":[122],"rather":[123],"than":[124],"implementation":[125],"shortfall":[126],"(IS)":[127],"or":[128],"shaped":[130,143],"function.":[132],"experimental":[134],"results":[135],"have":[136],"demonstrated":[137],"advantages":[138],"over":[139],"IS":[140],"function":[145],"terms":[147],"performance":[149],"simplicity.":[151],"has":[155],"outperformed":[156],"industry":[158],"commonly":[159],"used":[160],"models":[162,177],"TWAP,":[165],"VWAP,":[166],"AC":[168],"well":[170],"several":[172],"Deep":[173],"Reinforcement":[174],"Learning":[175],"(DRL)":[176],"14":[182],"US":[183],"equities":[184],"our":[186],"experiments.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}