{"id":"https://openalex.org/W4405785416","doi":"https://doi.org/10.1109/iros58592.2024.10801730","title":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","display_name":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785416","doi":"https://doi.org/10.1109/iros58592.2024.10801730"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5011989897","display_name":"Ameya Pore","orcid":"https://orcid.org/0000-0001-7380-6118"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ameya Pore","raw_affiliation_strings":["University of Verona,Department of Engineering for Innovation Medicine,Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona,Department of Engineering for Innovation Medicine,Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001597507","display_name":"Riccardo Muradore","orcid":"https://orcid.org/0000-0002-0287-6896"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Muradore","raw_affiliation_strings":["University of Verona,Department of Engineering for Innovation Medicine,Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona,Department of Engineering for Innovation Medicine,Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072250553","display_name":"Diego Dall\u2019Alba","orcid":"https://orcid.org/0000-0002-7300-5975"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Diego Dall\u2019Alba","raw_affiliation_strings":["University of Verona,Department of Engineering for Innovation Medicine,Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona,Department of Engineering for Innovation Medicine,Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011989897"],"corresponding_institution_ids":["https://openalex.org/I119439378"],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70582161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9162999987602234,"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":0.9162999987602234,"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":0.8033357858657837},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7159052491188049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41723668575286865}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8033357858657837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159052491188049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41723668575286865}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3091277626","https://openalex.org/W3173518742","https://openalex.org/W3175558129","https://openalex.org/W4252279978","https://openalex.org/W4390873444","https://openalex.org/W4390874575","https://openalex.org/W6682849425","https://openalex.org/W6769035977","https://openalex.org/W6776867236","https://openalex.org/W6779827379","https://openalex.org/W6780559457","https://openalex.org/W6784556858","https://openalex.org/W6787713516","https://openalex.org/W6788031615","https://openalex.org/W6799458897","https://openalex.org/W6810343060","https://openalex.org/W6839804929","https://openalex.org/W6841008801","https://openalex.org/W6853042979","https://openalex.org/W6856741353"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"algorithms":[3],"can":[4,42],"learn":[5,73],"robotic":[6],"control":[7,131],"tasks":[8],"from":[9],"visual":[10,24,48,95,165],"observations,":[11],"but":[12],"they":[13],"often":[14],"require":[15,92],"a":[16,53],"large":[17],"amount":[18],"of":[19,39,47,67,76,94,119],"data,":[20],"especially":[21],"when":[22],"the":[23,36,44,64,68,77,80,107,111,116,120,169],"scene":[25],"is":[26],"complex":[27],"and":[28,58,79,133,176],"unstructured.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"explore":[34],"how":[35],"agent\u2019s":[37],"knowledge":[38,163],"its":[40],"shape":[41],"improve":[43],"sample":[45,147],"efficiency":[46,175],"RL":[49,108,166],"methods.":[50],"We":[51,122],"propose":[52],"novel":[54],"method,":[55],"Disentangled":[56],"Environment":[57],"Agent":[59],"Representations":[60],"(DEAR),":[61],"that":[62,141,160],"uses":[63],"segmentation":[65],"mask":[66],"agent":[69,81,112,162],"as":[70,102],"supervision":[71],"to":[72,106,113,171],"disentangled":[74],"representations":[75,98],"environment":[78],"through":[82],"feature":[83],"separation":[84],"constraints.":[85],"Unlike":[86],"previous":[87],"approaches,":[88],"DEAR":[89,124,142],"does":[90],"not":[91],"reconstruction":[93],"observations.":[96],"These":[97],"are":[99],"then":[100],"used":[101],"an":[103],"auxiliary":[104],"loss":[105],"objective,":[109],"encouraging":[110],"focus":[114],"on":[115,125],"relevant":[117],"features":[118],"environment.":[121],"evaluate":[123],"two":[126],"challenging":[127],"benchmarks:":[128],"Distracting":[129],"DeepMind":[130],"suite":[132],"Franka":[134],"Kitchen":[135],"manipulation":[136],"tasks.":[137],"Our":[138,157],"findings":[139],"demonstrate":[140],"surpasses":[143],"state-of-the-art":[144],"methods":[145,167],"in":[146],"efficiency,":[148],"achieving":[149],"comparable":[150],"or":[151],"superior":[152],"performance":[153],"with":[154],"reduced":[155],"parameters.":[156],"results":[158],"indicate":[159],"integrating":[161],"into":[164],"has":[168],"potential":[170],"enhance":[172],"their":[173],"learning":[174],"robustness.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}