{"id":"https://openalex.org/W4205964938","doi":"https://doi.org/10.1109/smc52423.2021.9658790","title":"A Deep Reinforcement Learning Approach to Learning Tree Edit Policies on Binary Trees","display_name":"A Deep Reinforcement Learning Approach to Learning Tree Edit Policies on Binary Trees","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4205964938","doi":"https://doi.org/10.1109/smc52423.2021.9658790"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9658790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658790","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083351329","display_name":"Shirin Shirvani","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shirin Shirvani","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1992","last_page":"1999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9980999827384949,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9980999827384949,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9973999857902527,"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/T10028","display_name":"Topic Modeling","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6911741495132446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6761161684989929},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6339150071144104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.566250205039978},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.5270193815231323},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.511749267578125},{"id":"https://openalex.org/keywords/interval-tree","display_name":"Interval tree","score":0.45620134472846985},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4238876700401306},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.42271849513053894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4185448884963989},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.41745468974113464},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.3906547427177429},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2711397409439087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1961614489555359}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6911741495132446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761161684989929},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6339150071144104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.566250205039978},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.5270193815231323},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.511749267578125},{"id":"https://openalex.org/C84927040","wikidata":"https://www.wikidata.org/wiki/Q6057306","display_name":"Interval tree","level":4,"score":0.45620134472846985},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4238876700401306},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.42271849513053894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4185448884963989},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.41745468974113464},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.3906547427177429},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2711397409439087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1961614489555359},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc52423.2021.9658790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658790","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2017719595","https://openalex.org/W2044789562","https://openalex.org/W2064675550","https://openalex.org/W2065722925","https://openalex.org/W2075958727","https://openalex.org/W2096642780","https://openalex.org/W2154851992","https://openalex.org/W2387282348","https://openalex.org/W3104097132","https://openalex.org/W4251205962","https://openalex.org/W4293651439","https://openalex.org/W6654813271","https://openalex.org/W6689723076","https://openalex.org/W6711092126","https://openalex.org/W6744557953"],"related_works":["https://openalex.org/W2107381954","https://openalex.org/W3022865202","https://openalex.org/W2501849745","https://openalex.org/W3169685561","https://openalex.org/W2117536196","https://openalex.org/W2906792929","https://openalex.org/W1510719821","https://openalex.org/W2382364329","https://openalex.org/W2022598760","https://openalex.org/W2067642082"],"abstract_inverted_index":{"Modeling":[0],"sequential":[1],"transformations":[2],"between":[3],"two":[4,66],"trees":[5],"is":[6,134],"a":[7,75,95,103,116,162,168],"fundamental":[8],"task":[9],"in":[10,36,74,88,122],"domains":[11],"such":[12],"as":[13],"bioinformatics.":[14],"Traditional":[15],"methods":[16],"to":[17,31,60,118,123,140,181],"address":[18],"this":[19,89,91],"usually":[20],"rely":[21],"on":[22,136],"hand-coded":[23],"heuristics":[24],"and":[25,40,53,78,97,115,179],"algorithms":[26],"which":[27,152],"are":[28],"often":[29],"hard":[30],"derive.":[32],"The":[33],"large":[34],"advances":[35],"deep":[37,163],"learning":[38,55,99,165],"technologies":[39],"computational":[41],"power":[42],"have":[43],"recently":[44],"opened":[45],"up":[46],"new":[47],"potential":[48],"avenues.":[49],"In":[50],"particular,":[51],"representation":[52,96,104,133],"policy":[54,98,117,188],"provides":[56],"an":[57,85,147,183],"interesting":[58],"opportunity":[59],"model":[61],"the":[62,124,132,154,192,196],"dynamic":[63],"evolution":[64,80],"of":[65,143],"trees,":[67],"where":[68],"each":[69],"tree":[70,109,121,127,137,186,194],"can":[71,81],"be":[72,82],"embedded":[73],"Euclidean":[76],"space":[77],"its":[79],"modeled":[83],"by":[84],"embedding":[86],"trajectory":[87],"space.In":[90],"paper,":[92],"we":[93],"propose":[94],"framework":[100],"that":[101,189],"learns":[102],"for":[105,171,175],"arbitrary":[106],"sized":[107],"binary":[108],"pairs":[110,142],"using":[111,128],"recurrent":[112],"LSTM":[113],"networks":[114],"transfer":[119,138,187],"one":[120],"corresponding":[125],"target":[126,197],"Reinforcement":[129],"Learning.":[130],"Here,":[131],"pre-trained":[135],"similarity":[139],"transform":[141],"tree-structured":[144],"data":[145],"into":[146,195],"approximate":[148],"numerical":[149],"multidimensional":[150],"vector":[151],"encodes":[153],"original":[155],"structure":[156],"information.":[157],"This":[158],"model,":[159],"used":[160],"with":[161],"reinforcement":[164],"approach,":[166],"yields":[167],"constructive":[169],"method":[170],"generating":[172],"basis":[173],"functions":[174,178],"approximating":[176],"value":[177],"permits":[180],"learn":[182],"efficient,":[184],"general":[185],"incrementally":[190],"transforms":[191],"source":[193],"tree.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}