{"id":"https://openalex.org/W4416749602","doi":"https://doi.org/10.1109/iros60139.2025.11247146","title":"Mastering the Labyrinth Game: Efficient Multimodal Reinforcement Learning with Selective Reconstruction","display_name":"Mastering the Labyrinth Game: Efficient Multimodal Reinforcement Learning with Selective Reconstruction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749602","doi":"https://doi.org/10.1109/iros60139.2025.11247146"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5036943270","display_name":"Thomas Bi","orcid":"https://orcid.org/0000-0002-3687-4864"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Thomas Bi","raw_affiliation_strings":["ETH Zurich,Institute for Dynamic Systems and Control,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Institute for Dynamic Systems and Control,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120617553","display_name":"Ethan Marot","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ethan Marot","raw_affiliation_strings":["ETH Zurich,Institute for Dynamic Systems and Control,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Institute for Dynamic Systems and Control,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087505557","display_name":"Aswin Ramachandran","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Aswin Ramachandran","raw_affiliation_strings":["ETH Zurich,Institute for Dynamic Systems and Control,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Institute for Dynamic Systems and Control,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050557198","display_name":"Raffaello D\u2019Andrea","orcid":"https://orcid.org/0000-0001-5287-7849"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Raffaello D\u2019Andrea","raw_affiliation_strings":["ETH Zurich,Institute for Dynamic Systems and Control,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Institute for Dynamic Systems and Control,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036943270"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20557773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9753","last_page":"9759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.21739999949932098,"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":0.21739999949932098,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.1014999970793724,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07370000332593918,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.832099974155426},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.511900007724762},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.3564999997615814},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3269999921321869},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3215999901294708},{"id":"https://openalex.org/keywords/learning-effect","display_name":"Learning effect","score":0.2904999852180481},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.2865000069141388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.832099974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.60589998960495},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3425999879837036},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C10431821","wikidata":"https://www.wikidata.org/wiki/Q6510174","display_name":"Learning effect","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":14,"referenced_works":["https://openalex.org/W1516655250","https://openalex.org/W1541354001","https://openalex.org/W1964339024","https://openalex.org/W2141559645","https://openalex.org/W2443711627","https://openalex.org/W3145547920","https://openalex.org/W3205091198","https://openalex.org/W3206200647","https://openalex.org/W4280571816","https://openalex.org/W4395690191","https://openalex.org/W4401413724","https://openalex.org/W4401415323","https://openalex.org/W4405785980","https://openalex.org/W4407951290"],"related_works":[],"abstract_inverted_index":{"In":[0,20],"previous":[1],"work,":[2],"model-based":[3],"reinforcement":[4],"learning":[5,16,73,91,131],"was":[6],"applied":[7],"to":[8,13,89,105,120],"a":[9],"real-world":[10],"labyrinth":[11],"game":[12],"demonstrate":[14],"sample-efficient":[15],"using":[17],"world":[18,70],"models.":[19],"this":[21],"paper,":[22],"we":[23,84],"further":[24],"enhance":[25],"sample":[26],"efficiency":[27],"and":[28,53,80,99,127],"autonomy":[29],"by":[30],"introducing":[31],"selective":[32],"reconstruction:":[33],"instead":[34],"of":[35,96],"reconstructing":[36],"the":[37,45,59,69,97,113],"full":[38],"visual":[39,61],"observation,":[40],"our":[41],"approach":[42],"reconstructs":[43],"only":[44],"low-dimensional":[46],"physical":[47],"state":[48],"signals":[49],"(e.g.,":[50],"marble":[51,103],"position":[52],"plate":[54],"inclination),":[55],"while":[56,123],"still":[57],"leveraging":[58],"complete":[60],"input":[62],"for":[63],"decision-making.":[64],"This":[65],"targeted":[66],"reconstruction":[67],"focuses":[68],"model":[71,81],"on":[72],"dynamics-relevant":[74],"information,":[75],"thereby":[76],"reducing":[77],"computational":[78],"overhead":[79],"complexity.":[82],"Additionally,":[83],"incorporate":[85],"prioritized":[86],"experience":[87,116],"replay":[88],"accelerate":[90],"in":[92],"newly":[93],"explored":[94],"regions":[95],"maze":[98],"implement":[100],"an":[101],"autonomous":[102,130],"reloader":[104],"eliminate":[106],"manual":[107],"resets.":[108],"Together,":[109],"these":[110],"enhancements":[111],"reduce":[112],"required":[114],"collected":[115],"from":[117],"5":[118],"hours":[119,122],"1.5":[121],"achieving":[124],"comparable":[125],"performance,":[126],"enable":[128],"fully":[129],"without":[132],"human":[133],"supervision.":[134]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}