{"id":"https://openalex.org/W4407404707","doi":"https://doi.org/10.1109/sii59315.2025.10870988","title":"Leveraging Symbolic Models in Reinforcement Learning for Multi-skill Chaining<sup>*</sup>","display_name":"Leveraging Symbolic Models in Reinforcement Learning for Multi-skill Chaining<sup>*</sup>","publication_year":2025,"publication_date":"2025-01-21","ids":{"openalex":"https://openalex.org/W4407404707","doi":"https://doi.org/10.1109/sii59315.2025.10870988"},"language":"en","primary_location":{"id":"doi:10.1109/sii59315.2025.10870988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii59315.2025.10870988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/SICE International Symposium on System Integration (SII)","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/A5023237216","display_name":"Wenhao Lu","orcid":"https://orcid.org/0000-0001-8660-2886"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wenhao Lu","raw_affiliation_strings":["Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003959756","display_name":"Maximilian Diehl","orcid":"https://orcid.org/0000-0001-9323-8293"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Maximilian Diehl","raw_affiliation_strings":["Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016897258","display_name":"Jonas Sj\u00f6berg","orcid":"https://orcid.org/0000-0003-2685-8083"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jonas Sj\u00f6berg","raw_affiliation_strings":["Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085467629","display_name":"Karinne Ram\u00edrez-Amaro","orcid":"https://orcid.org/0000-0003-4600-1722"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Karinne Ramirez-Amaro","raw_affiliation_strings":["Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90084757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9904000163078308,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9904000163078308,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9857000112533569,"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/chaining","display_name":"Chaining","score":0.8475369215011597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373292446136475},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6922975182533264},{"id":"https://openalex.org/keywords/backward-chaining","display_name":"Backward chaining","score":0.4465300738811493},{"id":"https://openalex.org/keywords/symbolic-execution","display_name":"Symbolic execution","score":0.4238613545894623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3980775773525238},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3497285544872284},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33790940046310425},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14800629019737244},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10523149371147156},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.0711938738822937}],"concepts":[{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.8475369215011597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373292446136475},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6922975182533264},{"id":"https://openalex.org/C129916263","wikidata":"https://www.wikidata.org/wiki/Q1141183","display_name":"Backward chaining","level":4,"score":0.4465300738811493},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.4238613545894623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3980775773525238},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3497285544872284},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33790940046310425},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14800629019737244},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10523149371147156},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.0711938738822937},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii59315.2025.10870988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii59315.2025.10870988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/SICE International Symposium on System Integration (SII)","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":29,"referenced_works":["https://openalex.org/W2031738727","https://openalex.org/W2158782408","https://openalex.org/W2161414194","https://openalex.org/W2308567354","https://openalex.org/W2899455150","https://openalex.org/W2963709735","https://openalex.org/W2973229164","https://openalex.org/W2975504670","https://openalex.org/W3165194156","https://openalex.org/W3176814369","https://openalex.org/W3204657926","https://openalex.org/W4319348618","https://openalex.org/W4403676968","https://openalex.org/W6616173779","https://openalex.org/W6703337927","https://openalex.org/W6734215269","https://openalex.org/W6741002519","https://openalex.org/W6748599296","https://openalex.org/W6749821205","https://openalex.org/W6758134627","https://openalex.org/W6763535664","https://openalex.org/W6780559895","https://openalex.org/W6784712800","https://openalex.org/W6785308759","https://openalex.org/W6797065961","https://openalex.org/W6804064799","https://openalex.org/W6808981493","https://openalex.org/W6843357306","https://openalex.org/W6849619839"],"related_works":["https://openalex.org/W2132414486","https://openalex.org/W2044830634","https://openalex.org/W2114383597","https://openalex.org/W2472912427","https://openalex.org/W2767696758","https://openalex.org/W4238340239","https://openalex.org/W2184441786","https://openalex.org/W2886511220","https://openalex.org/W2001235946","https://openalex.org/W2129428592"],"abstract_inverted_index":{"We":[0],"envision":[1],"robots":[2],"learning":[3,21,96,147],"new":[4,86],"skills":[5,138,163],"as":[6,8,24,182],"efficiently":[7],"possible.":[9],"A":[10],"key":[11],"challenge":[12],"in":[13,35,49,98,198],"this":[14,56],"pursuit":[15],"is":[16,152,209],"that":[17,76,88],"the":[18,30,36,50,60,64,125],"efficiency":[19,97,110,190],"of":[20,38,42,67,127],"systems":[22],"such":[23,181],"Reinforcement":[25],"Learning":[26],"(RL)":[27],"deteriorates":[28],"with":[29,55,124,154,173,217],"task":[31,37,104,121,150],"complexity.":[32],"For":[33],"instance,":[34],"building":[39],"a":[40,85],"tower":[41],"cubes,":[43,185],"multiple":[44],"subtasks":[45],"must":[46],"be":[47],"executed":[48],"correct":[51,65],"sequence":[52,61],"to":[53,94,135,202,211,213,237],"succeed":[54],"long-horizon":[57,99],"task.":[58],"As":[59],"extends,":[62],"determining":[63],"order":[66],"actions":[68],"becomes":[69],"increasingly":[70],"difficult,":[71],"particularly":[72],"for":[73,111,139,170,191],"RL":[74,93,112,133,204],"methods":[75],"rely":[77],"on":[78,120],"trial-and-error.":[79],"To":[80],"tackle":[81],"this,":[82],"we":[83],"propose":[84],"method":[87,208],"integrates":[89],"symbolic":[90],"models":[91,102],"into":[92],"boost":[95],"tasks.":[100],"Symbolic":[101],"offer":[103],"abstraction":[105],"and":[106,165],"can":[107],"enhance":[108],"sample":[109,189],"agents":[113,134],"through":[114],"high-level":[115],"operators.":[116],"Our":[117],"approach":[118,194],"focuses":[119],"decomposition":[122,151],"aligned":[123],"structure":[126],"Automated":[128],"Planning":[129],"(AP)":[130],"operators,":[131],"enabling":[132],"synthesize":[136],"individual":[137],"specific":[140],"subtasks,":[141],"thus":[142],"they":[143],"will":[144],"require":[145],"fewer":[146],"samples.":[148],"The":[149],"designed":[153],"dual":[155],"consideration:":[156],"1)":[157],"reducing":[158],"errors":[159],"when":[160],"linking":[161],"subsequent":[162],"together":[164],"2)":[166],"enhancing":[167],"skill":[168],"reusability":[169],"downstream":[171],"tasks":[172,216],"similar":[174],"structures.":[175],"In":[176],"simulated":[177],"robot":[178],"manipulation":[179],"tasks,":[180],"stacking":[183],"two":[184],"experiments":[186],"demonstrate":[187],"superior":[188],"our":[192,207],"proposed":[193],"(a":[195],"2x":[196],"reduction":[197],"training":[199],"cost)":[200],"compared":[201],"most":[203],"baselines.":[205],"Furthermore,":[206],"robust":[210],"generalise":[212],"unseen":[214],"rearrangement":[215],"minimal":[218],"interaction":[219],"steps":[220],"(fewer":[221],"than":[222,232],"100),":[223],"achieving":[224],"an":[225],"average":[226],"success":[227],"rate":[228],"approximately":[229],"50%":[230],"higher":[231],"baselines,":[233],"which":[234],"often":[235],"struggle":[236],"make":[238],"progress.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}