{"id":"https://openalex.org/W4415398667","doi":"https://doi.org/10.1109/icdl63968.2025.11204430","title":"Robots that Learn to Solve Symbolic Novelties with Self-Generated RL Simulations","display_name":"Robots that Learn to Solve Symbolic Novelties with Self-Generated RL Simulations","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415398667","doi":"https://doi.org/10.1109/icdl63968.2025.11204430"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","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/A5079601359","display_name":"Christopher Thierauf","orcid":"https://orcid.org/0000-0002-5650-2574"},"institutions":[{"id":"https://openalex.org/I66958751","display_name":"Woods Hole Oceanographic Institution","ror":"https://ror.org/03zbnzt98","country_code":"US","type":"funder","lineage":["https://openalex.org/I66958751"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Thierauf","raw_affiliation_strings":["Woods Hole Oceanographic Institution, Woods Hole,Deep Submergence Laboratory,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Woods Hole Oceanographic Institution, Woods Hole,Deep Submergence Laboratory,MA,USA","institution_ids":["https://openalex.org/I66958751"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044523801","display_name":"Matthias Scheutz","orcid":"https://orcid.org/0000-0002-0064-2789"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias Scheutz","raw_affiliation_strings":["Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9900000095367432,"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":0.9900000095367432,"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":0.98089998960495,"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"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/construct","display_name":"Construct (python library)","score":0.755299985408783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7028999924659729},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6621000170707703},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.6453999876976013},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6154999732971191},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3431999981403351},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.3260999917984009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76910001039505},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.755299985408783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7028999924659729},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6621000170707703},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"well-known":[1],"challenge":[2],"with":[3,166],"symbolic":[4,47],"systems":[5],"is":[6,124],"that":[7,14,44,90,121],"they":[8,16],"are":[9],"constrained":[10],"by":[11,41,141],"their":[12],"domain:":[13],"is,":[15],"require":[17],"a":[18,35,114,125],"predetermined":[19],"set":[20],"of":[21],"facts":[22],"to":[23,28,38,97,112,155,180,195],"compute":[24],"over":[25],"and":[26,68,88,106,132,150,192],"struggle":[27],"handle":[29],"novelty.":[30],"Machine":[31],"learning":[32],"techniques":[33],"offer":[34],"potential":[36],"resolution":[37],"this":[39,50,86,109,136,164],"problem":[40],"allowing":[42],"exploration":[43,145],"expands":[45],"the":[46,54,71,75,128,133,142,147,157,173,178,183],"domain.":[48],"To":[49],"end,":[51],"we":[52,119],"describe":[53],"\u201creal-sim-real\u201d":[55],"problem,":[56,87],"where":[57,172],"an":[58,82,91],"agent":[59,92,143,174],"must":[60],"construct":[61,98],"its":[62,99],"own":[63,100],"simulation":[64,76,101,130],"environment":[65,131,179,184],"for":[66],"training":[67,194],"then":[69,80,107,151],"deploy":[70],"learned":[72],"policy":[73],"(correcting":[74],"as":[77],"necessary).":[78],"We":[79,162],"present":[81],"approach":[83],"which":[84,188],"addresses":[85],"demonstrate":[89],"can":[93,138],"use":[94,108],"sensor":[95],"data":[96],"environment,":[102,135],"train":[103],"in":[104,146,197],"it,":[105],"newly-obtained":[110],"knowledge":[111],"solve":[113,156],"task":[115,159],"planning":[116,160],"problem.":[117,161],"Further,":[118],"show":[120],"when":[122],"there":[123],"mismatch":[126,137],"between":[127],"generated":[129],"real":[134,148,198],"be":[139,152,186],"resolved":[140],"through":[144],"world,":[149],"again":[153],"applied":[154],"better-understood":[158],"integrate":[163],"work":[165,168],"prior":[167],"on":[169,177],"object-centric":[170],"policies,":[171],"trains":[175],"directly":[176],"understand":[181],"how":[182],"should":[185],"manipulated,":[187],"improves":[189],"sim-to-real":[190],"transfer":[191],"allows":[193],"occur":[196],"time.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-22T00:00:00"}