{"id":"https://openalex.org/W4382239835","doi":"https://doi.org/10.1609/aaai.v37i4.25521","title":"Reinforcement Learning for Branch-and-Bound Optimisation Using Retrospective Trajectories","display_name":"Reinforcement Learning for Branch-and-Bound Optimisation Using Retrospective Trajectories","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382239835","doi":"https://doi.org/10.1609/aaai.v37i4.25521"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v37i4.25521","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i4.25521","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25521/25293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25521/25293","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008149746","display_name":"Christopher W. F. Parsonson","orcid":"https://orcid.org/0000-0002-2366-7081"},"institutions":[{"id":"https://openalex.org/I2801187875","display_name":"University College Lahore","ror":"https://ror.org/0572v5y16","country_code":"PK","type":"education","lineage":["https://openalex.org/I2801187875"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Christopher W. F. Parsonson","raw_affiliation_strings":["UCL"],"affiliations":[{"raw_affiliation_string":"UCL","institution_ids":["https://openalex.org/I2801187875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069279442","display_name":"Alexandre Laterre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Laterre","raw_affiliation_strings":["InstaDeep"],"affiliations":[{"raw_affiliation_string":"InstaDeep","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052796575","display_name":"Thomas D. Barrett","orcid":"https://orcid.org/0000-0001-6241-3028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas D. Barrett","raw_affiliation_strings":["InstaDeep"],"affiliations":[{"raw_affiliation_string":"InstaDeep","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008149746"],"corresponding_institution_ids":["https://openalex.org/I2801187875"],"apc_list":null,"apc_paid":null,"fwci":1.8058,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8677772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"4","first_page":"4061","last_page":"4069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9930999875068665,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9930999875068665,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9843999743461609,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8127966523170471},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7614834308624268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6383296847343445},{"id":"https://openalex.org/keywords/branch-and-bound","display_name":"Branch and bound","score":0.5461039543151855},{"id":"https://openalex.org/keywords/branching","display_name":"Branching (polymer chemistry)","score":0.5449756979942322},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5404108762741089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344212651252747},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.515373170375824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4844929873943329},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4687780439853668},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4125930368900299},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3066292405128479},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.2994838356971741},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25234049558639526}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8127966523170471},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7614834308624268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6383296847343445},{"id":"https://openalex.org/C93693863","wikidata":"https://www.wikidata.org/wiki/Q897659","display_name":"Branch and bound","level":2,"score":0.5461039543151855},{"id":"https://openalex.org/C206175624","wikidata":"https://www.wikidata.org/wiki/Q595731","display_name":"Branching (polymer chemistry)","level":2,"score":0.5449756979942322},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5404108762741089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344212651252747},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.515373170375824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4844929873943329},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4687780439853668},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4125930368900299},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3066292405128479},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2994838356971741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25234049558639526},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v37i4.25521","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i4.25521","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25521/25293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v37i4.25521","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i4.25521","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25521/25293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382239835.pdf"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W83093243","https://openalex.org/W626292722","https://openalex.org/W1557310162","https://openalex.org/W1573881838","https://openalex.org/W1583961104","https://openalex.org/W1999049191","https://openalex.org/W2013520638","https://openalex.org/W2056132907","https://openalex.org/W2060514920","https://openalex.org/W2091364465","https://openalex.org/W2098248004","https://openalex.org/W2118518847","https://openalex.org/W2165085685","https://openalex.org/W2167580124","https://openalex.org/W2171074980","https://openalex.org/W2173248099","https://openalex.org/W2179366033","https://openalex.org/W2201581102","https://openalex.org/W2222122796","https://openalex.org/W2257979135","https://openalex.org/W2499865049","https://openalex.org/W2563592268","https://openalex.org/W2576311753","https://openalex.org/W2626188202","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2779977383","https://openalex.org/W2859870583","https://openalex.org/W2900896126","https://openalex.org/W2904157920","https://openalex.org/W2948268323","https://openalex.org/W2960567166","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2970868077","https://openalex.org/W3032628781","https://openalex.org/W3041202696","https://openalex.org/W3047863327","https://openalex.org/W3090460193","https://openalex.org/W3100248546","https://openalex.org/W3129322645","https://openalex.org/W3131262006","https://openalex.org/W3173319990","https://openalex.org/W3188522200","https://openalex.org/W3211731195","https://openalex.org/W4240374930","https://openalex.org/W4287549149","https://openalex.org/W4287998216","https://openalex.org/W4288029271","https://openalex.org/W4298857966","https://openalex.org/W4300704005","https://openalex.org/W6634868215","https://openalex.org/W6637967152","https://openalex.org/W6664976405","https://openalex.org/W6665998705","https://openalex.org/W6684294211","https://openalex.org/W6685155065","https://openalex.org/W6687681856","https://openalex.org/W6689051861","https://openalex.org/W6730575273","https://openalex.org/W6739987476","https://openalex.org/W6745620495","https://openalex.org/W6756303580","https://openalex.org/W6766967640","https://openalex.org/W6780394890","https://openalex.org/W6790748592"],"related_works":["https://openalex.org/W2165085685","https://openalex.org/W2752534598","https://openalex.org/W2741597579","https://openalex.org/W1978745934","https://openalex.org/W2366206435","https://openalex.org/W2277678953","https://openalex.org/W3006406045","https://openalex.org/W3173319990","https://openalex.org/W27222569","https://openalex.org/W4248516644"],"abstract_inverted_index":{"Combinatorial":[0],"optimisation":[1],"problems":[2],"framed":[3],"as":[4,47,63,87],"mixed":[5],"integer":[6],"linear":[7],"programmes":[8],"(MILPs)":[9],"are":[10,213],"ubiquitous":[11],"across":[12],"a":[13,29,64,124,145],"range":[14],"of":[15,32,50,109,191],"real-world":[16],"applications.":[17],"The":[18],"canonical":[19],"branch-and-bound":[20],"algorithm":[21,184],"seeks":[22],"to":[23,54,74,95,129,151,215],"exactly":[24],"solve":[25],"MILPs":[26,198],"by":[27,185],"constructing":[28],"search":[30,137],"tree":[31,138],"increasingly":[33],"constrained":[34],"sub-problems.":[35],"In":[36,117,161],"practice,":[37],"its":[38],"solving":[39],"time":[40],"performance":[41,196],"is":[42],"dependent":[43],"on":[44,163,197],"heuristics,":[45],"such":[46],"the":[48,51,107,136,149,179,192],"choice":[49],"next":[52,159],"variable":[53],"constrain":[55],"('branching').":[56],"Recently,":[57],"machine":[58],"learning":[59,77,103],"(ML)":[60],"has":[61],"emerged":[62],"promising":[65],"paradigm":[66],"for":[67,131],"branching.":[68,132],"However,":[69],"prior":[70],"works":[71],"have":[72],"struggled":[73],"apply":[75],"reinforcement":[76],"(RL),":[78],"citing":[79],"sparse":[80],"rewards,":[81],"difficult":[82],"exploration,":[83],"and":[84,112,187,202],"partial":[85],"observability":[86],"significant":[88],"challenges.":[89],"Instead,":[90],"leading":[91],"ML":[92],"methodologies":[93],"resort":[94],"approximating":[96],"high":[97],"quality":[98],"handcrafted":[99],"heuristics":[100],"with":[101,156,199,205],"imitation":[102],"(IL),":[104],"which":[105],"precludes":[106],"discovery":[108],"novel":[110],"policies":[111],"requires":[113],"expensive":[114],"data":[115],"labelling.":[116],"this":[118],"work,":[119],"we":[120,147],"propose":[121],"retro":[122],"branching;":[123],"simple":[125],"yet":[126],"effective":[127],"approach":[128,168],"RL":[130,182],"By":[133],"retrospectively":[134,210],"deconstructing":[135],"into":[139],"multiple":[140],"paths":[141],"each":[142],"contained":[143],"within":[144,189],"sub-tree,":[146],"enable":[148],"agent":[150],"learn":[152],"from":[153],"shorter":[154],"trajectories":[155,212],"more":[157],"predictable":[158],"states.":[160],"experiments":[162],"four":[164],"combinatorial":[165],"tasks,":[166],"our":[167,209],"enables":[169],"learning-to-branch":[170],"without":[171],"any":[172],"expert":[173],"guidance":[174],"or":[175],"pre-training.":[176],"We":[177],"outperform":[178],"current":[180],"state-of-the-art":[181],"branching":[183],"3-5x":[186],"come":[188],"20%":[190],"best":[193],"IL":[194],"method's":[195],"500":[200],"constraints":[201],"1000":[203],"variables,":[204],"ablations":[206],"verifying":[207],"that":[208],"constructed":[211],"essential":[214],"achieving":[216],"these":[217],"results.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}