{"id":"https://openalex.org/W7151616067","doi":"https://doi.org/10.1109/icmla66185.2025.00094","title":"Mamba World Model for RL: Enhancing Long-term Memory in Model-based Reinforcement Learning","display_name":"Mamba World Model for RL: Enhancing Long-term Memory in Model-based Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151616067","doi":"https://doi.org/10.1109/icmla66185.2025.00094"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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/A5113373459","display_name":"Mingcong Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingcong Cao","raw_affiliation_strings":["University of Wisconsin&#x2013;Madison,Dept. of ECE,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin&#x2013;Madison,Dept. of ECE,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103481141","display_name":"Yu-Bi Huang","orcid":"https://orcid.org/0000-0002-6597-0425"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yucheng Huang","raw_affiliation_strings":["University of Wisconsin&#x2013;Madison,Dept. of ECE &amp; CS,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin&#x2013;Madison,Dept. of ECE &amp; CS,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052240751","display_name":"Suat G\u00fcm\u00fc\u015fsoy","orcid":"https://orcid.org/0000-0003-2064-3196"},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suat Gumussoy","raw_affiliation_strings":["Siemens Corporate Technology,Princeton,USA"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Technology,Princeton,USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084255924","display_name":"\u00dcmit Y. Ogras","orcid":"https://orcid.org/0000-0002-5045-5535"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umit Y. Ogras","raw_affiliation_strings":["University of Wisconsin&#x2013;Madison,Dept. of ECE,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin&#x2013;Madison,Dept. of ECE,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113373459"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87298434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"655","last_page":"662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8507999777793884,"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":0.8507999777793884,"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":0.020600000396370888,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reinforcement","display_name":"Reinforcement","score":0.5519999861717224},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3813999891281128},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24709999561309814},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.24660000205039978}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4260999858379364},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3644999861717224},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.24819999933242798},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.24660000205039978},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.22100000083446503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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":12,"referenced_works":["https://openalex.org/W1980035368","https://openalex.org/W2150468603","https://openalex.org/W2761873684","https://openalex.org/W2877093712","https://openalex.org/W2963403143","https://openalex.org/W2989847975","https://openalex.org/W3094502228","https://openalex.org/W4382317903","https://openalex.org/W4385245566","https://openalex.org/W4413431245","https://openalex.org/W7133196033","https://openalex.org/W7133201496"],"related_works":[],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1],"learning":[2,55],"(MBRL)":[3],"has":[4],"achieved":[5],"strong":[6],"results":[7],"in":[8,114,140],"numerous":[9],"challenging":[10,142],"domains":[11],"with":[12,122,162],"visual":[13],"inputs.":[14],"Its":[15],"success":[16],"relies":[17],"on":[18,160,165],"training":[19,173],"a":[20,93,100,119],"robust":[21],"world":[22,95],"model":[23,96,158],"that":[24,98],"not":[25],"only":[26],"captures":[27],"the":[28,31,131,141,166],"dynamics":[29],"of":[30],"environment":[32],"but":[33,57],"also":[34],"generates":[35],"rich,":[36],"imagined":[37],"trajectories":[38],"from":[39,64],"minimal":[40],"real-world":[41],"interactions.":[42],"Recurrent":[43,133],"Neural":[44],"Networks":[45],"(RNNs)":[46],"and":[47,76,112,136],"Transformers":[48,69,113],"are":[49],"commonly":[50],"used":[51],"for":[52],"such":[53],"sequential":[54],"tasks,":[56],"both":[58],"have":[59,70],"their":[60,84],"drawbacks:":[61],"RNNs":[62,111],"suffer":[63],"poor":[65],"long-term":[66,151],"memory,":[67],"while":[68,117,170],"O(n<sup":[71],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>)":[73],"inference":[74,124],"complexity":[75],"linearly":[77],"growing":[78],"KV":[79],"cache,":[80],"which":[81],"can":[82],"restrict":[83],"ability":[85,148],"to":[86,104,149],"handle":[87],"long":[88],"contexts":[89],"effectively.":[90],"We":[91],"present":[92],"Mamba-based":[94],"(MWM)":[97],"incorporates":[99],"novel":[101],"entropy":[102],"term":[103],"enhance":[105],"sample":[106,115],"efficiency.":[107],"Our":[108],"approach":[109,129],"matches":[110],"efficiency":[116],"supporting":[118],"longer":[120],"history":[121],"O(1)":[123],"complexity.":[125],"The":[126],"proposed":[127],"MWM":[128],"outperforms":[130],"Gated":[132],"Unit":[134],"(GRU)":[135],"Transformer-based":[137],"state-of-the-art":[138,163],"techniques":[139],"Minigrid":[143],"Memory":[144],"task,":[145],"showcasing":[146],"its":[147],"capture":[150],"dependencies":[152],"accurately.":[153],"Moreover,":[154],"our":[155],"19.7":[156],"million-parameter":[157],"performs":[159],"par":[161],"methods":[164],"Atari":[167],"100k":[168],"benchmark":[169],"having":[171],"lower":[172],"times":[174],"than":[175],"other":[176],"PyTorch-based":[177],"MBRL":[178],"algorithms.":[179]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}