{"id":"https://openalex.org/W3212482189","doi":"https://doi.org/10.7916/d8-7b4y-dk07","title":"Reinforcement Learning: New Algorithms and An Application for Integer Programming","display_name":"Reinforcement Learning: New Algorithms and An Application for Integer Programming","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3212482189","doi":"https://doi.org/10.7916/d8-7b4y-dk07","mag":"3212482189"},"language":"en","primary_location":{"id":"mag:3212482189","is_oa":false,"landing_page_url":"https://academiccommons.columbia.edu/doi/10.7916/d8-7b4y-dk07","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8-7b4y-dk07","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002692470","display_name":"Yunhao Tang","orcid":"https://orcid.org/0009-0001-2387-729X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tang, Yunhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002692470"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16525297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T14011","display_name":"Elevator Systems and Control","score":0.7168999910354614,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.7168999910354614,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.6754000186920166,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.614300012588501,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.6652183532714844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5719176530838013},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.4973912537097931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4705424904823303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42774683237075806}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6652183532714844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5719176530838013},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.4973912537097931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4705424904823303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42774683237075806}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:3212482189","is_oa":false,"landing_page_url":"https://academiccommons.columbia.edu/doi/10.7916/d8-7b4y-dk07","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.7916/d8-7b4y-dk07","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8-7b4y-dk07","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.7916/d8-7b4y-dk07","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8-7b4y-dk07","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2976992456","https://openalex.org/W3020831056","https://openalex.org/W3102856533","https://openalex.org/W2294642425","https://openalex.org/W2090089645","https://openalex.org/W1677462884","https://openalex.org/W2513959168","https://openalex.org/W1567083983","https://openalex.org/W2100357080","https://openalex.org/W2144522827","https://openalex.org/W2904417526","https://openalex.org/W2109682570","https://openalex.org/W2110362468","https://openalex.org/W3091528360","https://openalex.org/W3195372803","https://openalex.org/W2886825742","https://openalex.org/W3012020335","https://openalex.org/W2162745921","https://openalex.org/W2042793992","https://openalex.org/W2081101802"],"abstract_inverted_index":{"Reinforcement":[0,249],"learning":[1,203,300],"(RL)":[2],"is":[3],"a":[4,98,104,121,144,168,245,286],"generic":[5],"paradigm":[6],"for":[7,251],"the":[8,17,45,66,76,173,197,207,218,229,271],"modeling":[9],"and":[10,59,154,236,298],"optimization":[11,153,302],"of":[12,48,65,78,106,175,209,220,231,248,288],"sequential":[13],"decision":[14],"making.":[15],"In":[16,89,132,239],"recent":[18],"decade,":[19],"progress":[20],"in":[21,28,223,308],"RL":[22,49,61,70,87,189,290],"research":[23,227],"has":[24],"brought":[25],"about":[26],"breakthroughs":[27],"several":[29],"applications,":[30,225],"ranging":[31],"from":[32,202],"playing":[33],"video":[34],"games,":[35,38],"mastering":[36],"board":[37],"to":[39,50,119,125,179,193,217,255],"controlling":[40],"simulated":[41],"robots.":[42],"To":[43,186],"bring":[44],"potential":[46],"benefits":[47],"other":[51,194],"domains,":[52],"two":[53,73],"elements":[54],"are":[55,75],"critical:":[56],"(1)":[57],"Efficient":[58],"general-purpose":[60],"algorithms;":[62],"(2)":[63],"Formulations":[64],"original":[67,198],"applications":[68,199],"into":[69],"problems.":[71],"These":[72],"points":[74],"focus":[77,243],"this":[79,160],"thesis.":[80],"We":[81],"start":[82],"by":[83,266],"developing":[84],"more":[85],"efficient":[86],"algorithms.":[88],"Chapter":[90,133,240],"2,":[91],"we":[92,135,162,205,242,268],"propose":[93,136,163],"Taylor":[94],"Expansion":[95],"Policy":[96,142,164],"Optimization,":[97,143],"model-free":[99],"algorithmic":[100,123],"framework":[101,115,146],"that":[102,147,270],"unifies":[103],"number":[105],"important":[107],"prior":[108,126],"work":[109],"as":[110,140,285],"special":[111],"cases.":[112],"This":[113,283],"unifying":[114],"also":[116],"allows":[117],"us":[118],"develop":[120],"natural":[122],"extension":[124],"work,":[127],"with":[128,214,262,294],"empirical":[129],"performance":[130,182,278],"gains.":[131],"3,":[134],"Monte-Carlo":[137,155],"Tree":[138],"Search":[139],"Regularized":[141],"model-based":[145],"draws":[148],"close":[149],"connections":[150],"between":[151],"policy":[152,177],"tree":[156],"search.":[157],"Building":[158],"on":[159,244],"insight,":[161],"Optimization":[165],"Zero":[166],"(POZero),":[167],"novel":[169],"algorithm":[170],"which":[171],"leverages":[172],"strengths":[174],"regularized":[176],"search":[178],"achieve":[180,305],"significant":[181,232,277,306],"gains":[183,279],"over":[184,280],"MuZero.":[185],"showcase":[187],"how":[188,289,299],"can":[190,291],"be":[191,292],"applied":[192],"domains":[195],"where":[196],"could":[200],"benefit":[201],"systems,":[204],"study":[206],"acceleration":[208,307],"integer":[210],"programming":[211],"(IP)":[212],"solvers":[213,222],"RL.":[215],"Due":[216],"ubiquity":[219],"IP":[221,296],"industrial":[224],"such":[226],"holds":[228],"promise":[230],"real":[233],"life":[234],"impacts":[235],"practical":[237],"values.":[238],"4,":[241],"particular":[246],"formulation":[247],"Learning":[250,254],"Integer":[252],"Programming:":[253],"Cut.":[256],"By":[257],"combining":[258],"cutting":[259,273],"plane":[260,274],"methods":[261],"selection":[263],"rules":[264],"learned":[265],"RL,":[267],"observe":[269],"RL-augmented":[272],"solver":[275],"achieves":[276],"traditional":[281],"heuristics.":[282],"serves":[284],"proof-of-concept":[287],"combined":[293],"general":[295],"solvers,":[297],"augmented":[301],"systems":[303],"might":[304],"general.":[309]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}