{"id":"https://openalex.org/W4402896765","doi":"https://doi.org/10.1109/tpami.2024.3469053","title":"Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search","display_name":"Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search","publication_year":2024,"publication_date":"2024-09-26","ids":{"openalex":"https://openalex.org/W4402896765","doi":"https://doi.org/10.1109/tpami.2024.3469053","pmid":"https://pubmed.ncbi.nlm.nih.gov/39325607"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3469053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3469053","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5012155625","display_name":"Wenqing Zheng","orcid":"https://orcid.org/0000-0002-8283-7511"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqing Zheng","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical Engineering, The University of Texas At Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-8283-7511","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas At Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081880239","display_name":"S P Sharan","orcid":"https://orcid.org/0000-0002-6298-6464"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. P. Sharan","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical Engineering, The University of Texas At Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-6298-6464","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas At Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101178345","display_name":"Zhiwen Fan","orcid":"https://orcid.org/0000-0002-8302-7465"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwen Fan","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical Engineering, The University of Texas At Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-8302-7465","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas At Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019815695","display_name":"Kuanxiang Wang","orcid":"https://orcid.org/0000-0003-4673-7975"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wang","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical Engineering, The University of Texas At Austin, USA"],"raw_orcid":"https://orcid.org/0000-0003-4673-7975","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas At Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035229194","display_name":"Yihan Xi","orcid":"https://orcid.org/0000-0002-3509-8058"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yihan Xi","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical Engineering, The University of Texas At Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-3509-8058","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas At Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048522863","display_name":"Zhangyang Wang","orcid":"https://orcid.org/0000-0002-2050-5693"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangyang Wang","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical Engineering, The University of Texas At Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-2050-5693","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas At Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":1.1504,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81824698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"47","issue":"1","first_page":"400","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9872999787330627,"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":0.9872999787330627,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.98089998960495,"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":0.6949623227119446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6883329749107361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6653910279273987},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6456197500228882},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5063527822494507},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5034839510917664},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48752185702323914},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.461182177066803},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44608938694000244},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22591754794120789},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14790061116218567}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6949623227119446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6883329749107361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653910279273987},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6456197500228882},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5063527822494507},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5034839510917664},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48752185702323914},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.461182177066803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44608938694000244},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22591754794120789},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14790061116218567},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3469053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3469053","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39325607","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39325607","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1604434652","https://openalex.org/W1935590542","https://openalex.org/W2129202132","https://openalex.org/W2158782408","https://openalex.org/W2555113260","https://openalex.org/W2570076534","https://openalex.org/W2612281180","https://openalex.org/W2761873684","https://openalex.org/W2899455150","https://openalex.org/W2910230154","https://openalex.org/W2937463840","https://openalex.org/W2963487534","https://openalex.org/W2963773324","https://openalex.org/W2966361623","https://openalex.org/W3016401366","https://openalex.org/W3111389438","https://openalex.org/W3116073702","https://openalex.org/W3206768895","https://openalex.org/W4223959013","https://openalex.org/W4289765664","https://openalex.org/W4400555669","https://openalex.org/W6635278232","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6687086880","https://openalex.org/W6692846177","https://openalex.org/W6726913060","https://openalex.org/W6741002519","https://openalex.org/W6743846187","https://openalex.org/W6749992176","https://openalex.org/W6750748340","https://openalex.org/W6751437432","https://openalex.org/W6763464472","https://openalex.org/W6772619266","https://openalex.org/W6773656828","https://openalex.org/W6773942789","https://openalex.org/W6775002999","https://openalex.org/W6780561946","https://openalex.org/W6791739513","https://openalex.org/W6802133931","https://openalex.org/W6810312951","https://openalex.org/W6840023044","https://openalex.org/W6846413013","https://openalex.org/W7046505727"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1604739066","https://openalex.org/W246815506","https://openalex.org/W2346891937"],"abstract_inverted_index":{"Learning":[0],"efficient":[1],"and":[2,43,65,79,92,142,159,175,177],"interpretable":[3],"policies":[4,32,121,171],"has":[5],"been":[6],"a":[7,112,184],"challenging":[8],"task":[9],"in":[10,15],"reinforcement":[11],"learning":[12,64,115,158],"(RL),":[13],"particularly":[14],"the":[16,30,140,151],"visual":[17,84],"RL":[18],"setting":[19],"with":[20,75,183],"complex":[21,98],"scenes.":[22],"While":[23],"neural":[24,154],"networks":[25,155],"have":[26,50,97],"achieved":[27],"competitive":[28],"performance,":[29],"resulting":[31],"are":[33,39,173],"often":[34],"over-parameterized":[35],"black":[36],"boxes":[37],"that":[38,52,117,164,172],"difficult":[40],"to":[41,60,82,138,168],"interpret":[42],"deploy":[44],"efficiently.":[45],"More":[46],"recent":[47],"SRL":[48,181],"frameworks":[49],"shown":[51],"high-level":[53],"domain-specific":[54],"programming":[55],"logic":[56],"can":[57,87],"be":[58],"designed":[59],"handle":[61],"both":[62],"policy":[63],"symbolic":[66,114,120,146,170,188],"planning.":[67],"However,":[68],"these":[69,103],"approaches":[70],"rely":[71],"on":[72],"coded":[73],"primitives":[74],"little":[76],"feature":[77,157],"learning,":[78],"when":[80,95],"applied":[81],"high-dimensional":[83],"scenes,":[85],"they":[86],"suffer":[88],"from":[89],"scalability":[90,143],"issues":[91],"perform":[93],"poorly":[94],"images":[96],"object":[99],"interactions.":[100],"To":[101],"address":[102],"challenges,":[104],"we":[105],"propose":[106],"Differentiable":[107],"Symbolic":[108],"Expression":[109],"Search":[110],"(DiffSES),":[111],"novel":[113],"approach":[116],"discovers":[118],"discrete":[119],"using":[122,127],"partially":[123],"differentiable":[124],"optimization.":[125,160],"By":[126],"object-level":[128],"abstractions":[129],"instead":[130],"of":[131,145,153,187],"raw":[132],"pixel-level":[133],"inputs,":[134],"DiffSES":[135,165],"is":[136,166],"able":[137,167],"leverage":[139],"simplicity":[141],"advantages":[144],"expressions,":[147],"while":[148],"also":[149],"incorporating":[150],"strengths":[152],"for":[156],"Our":[161],"experiments":[162],"demonstrate":[163],"generate":[169],"simpler":[174],"more":[176],"scalable":[178],"than":[179],"state-of-the-art":[180],"methods,":[182],"reduced":[185],"amount":[186],"prior":[189],"knowledge.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}