{"id":"https://openalex.org/W4416251464","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228096","title":"M-SAT: Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Actions","display_name":"M-SAT: Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Actions","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251464","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228096"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5070606815","display_name":"Perusha Moodley","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Perusha Moodley","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100019160","display_name":"Dhillu Thambi","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhillu Thambi","raw_affiliation_strings":["International Institute of Information Technology,Machine Learning Lab,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Machine Learning Lab,Hyderabad,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100019161","display_name":"Mark Trovinger","orcid":null},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Trovinger","raw_affiliation_strings":["Mississippi State University,Dept. of Computer Science & Engineering,Starkville,MS,USA"],"affiliations":[{"raw_affiliation_string":"Mississippi State University,Dept. of Computer Science & Engineering,Starkville,MS,USA","institution_ids":["https://openalex.org/I99041443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035229102","display_name":"Pramod Kaushik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pramod Kaushik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000689728","display_name":"Praveen Paruchuri","orcid":"https://orcid.org/0000-0001-8071-5409"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praveen Paruchuri","raw_affiliation_strings":["International Institute of Information Technology,Machine Learning Lab,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Machine Learning Lab,Hyderabad,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040237916","display_name":"Hong Xia","orcid":"https://orcid.org/0000-0002-5875-0125"},"institutions":[{"id":"https://openalex.org/I71052956","display_name":"University of Reading","ror":"https://ror.org/05v62cm79","country_code":"GB","type":"education","lineage":["https://openalex.org/I71052956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xia Hong","raw_affiliation_strings":["University of Reading,School of Mathematical, Physical & Computational Sciences,Reading,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Reading,School of Mathematical, Physical & Computational Sciences,Reading,United Kingdom","institution_ids":["https://openalex.org/I71052956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068297734","display_name":"Benjamin Rosman","orcid":"https://orcid.org/0000-0002-0284-4114"},"institutions":[{"id":"https://openalex.org/I192619145","display_name":"University of the Witwatersrand","ror":"https://ror.org/03rp50x72","country_code":"ZA","type":"education","lineage":["https://openalex.org/I192619145"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Benjamin Rosman","raw_affiliation_strings":["University of the Witwatersrand,School of Computer Science and Applied Mathematics,Johannesburg,South Africa"],"affiliations":[{"raw_affiliation_string":"University of the Witwatersrand,School of Computer Science and Applied Mathematics,Johannesburg,South Africa","institution_ids":["https://openalex.org/I192619145"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070606815"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19472449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5760999917984009,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5760999917984009,"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":0.08089999854564667,"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":0.0706000030040741,"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/interpretability","display_name":"Interpretability","score":0.8723999857902527},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.559499979019165},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48820000886917114},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/decision-support-system","display_name":"Decision support system","score":0.33489999175071716},{"id":"https://openalex.org/keywords/decision-model","display_name":"Decision model","score":0.32829999923706055},{"id":"https://openalex.org/keywords/unexpected-events","display_name":"Unexpected events","score":0.2955000102519989}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8723999857902527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959999799728394},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.5062000155448914},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48820000886917114},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C2986909951","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision system","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:centaur.reading.ac.uk:127299","is_oa":false,"landing_page_url":"https://centaur.reading.ac.uk/view/creators/90000432.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402273","display_name":"CentAUR (University of Reading)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71052956","host_organization_name":"University of Reading","host_organization_lineage":["https://openalex.org/I71052956"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2963871073","https://openalex.org/W3094236223","https://openalex.org/W3162090017","https://openalex.org/W3174281149","https://openalex.org/W3185847553","https://openalex.org/W4286716185","https://openalex.org/W4300594522","https://openalex.org/W4312909062","https://openalex.org/W4385245566","https://openalex.org/W4386385595","https://openalex.org/W6884305255"],"related_works":[],"abstract_inverted_index":{"Effective":[0],"decision-making":[1,83,225],"in":[2,16,25,32,59,63,139,226],"complex":[3,137],"environments":[4,33,141],"with":[5,157,184,206],"multi-discrete":[6,38,143,158,227],"action":[7,90,144,159,228],"spaces":[8,160],"poses":[9],"significant":[10,189],"challenges":[11],"for":[12],"agent":[13,82,120],"architectures,":[14],"particularly":[15],"image-based":[17,162],"settings.":[18],"While":[19],"Decision":[20,43,182],"Transformers":[21],"have":[22,46],"shown":[23],"promise":[24],"various":[26],"domains,":[27],"their":[28,54],"performance":[29,104,178],"often":[30],"suffers":[31],"where":[34],"agents":[35,58,106,133],"must":[36],"handle":[37],"actions.":[39],"Existing":[40],"enhancements":[41],"to":[42,48,56,80,180,202,211],"Transformer":[44],"architectures":[45],"yet":[47],"address":[49,67],"this":[50,68],"critical":[51],"issue,":[52],"limiting":[53],"ability":[55],"support":[57],"learning":[60],"robust":[61],"policies":[62],"these":[64],"environments.":[65],"To":[66],"gap,":[69],"we":[70,193],"propose":[71],"Multi-State":[72],"Action":[73],"Tokenisation":[74],"(M-SAT),":[75],"a":[76],"novel":[77],"approach":[78,175],"designed":[79],"improve":[81],"by":[84],"tokenising":[85],"actions":[86,100,112],"at":[87],"the":[88,103,108,126,150],"individual":[89,111],"level":[91],"and":[92,107,131,161,171,222],"incorporating":[93],"auxiliary":[94],"state":[95],"information.":[96],"This":[97],"disentanglement":[98],"of":[99,105,110,128,135],"improves":[101],"both":[102],"interpretability":[109],"within":[113],"attention":[114],"layers,":[115],"fostering":[116],"better":[117],"visibility":[118],"into":[119],"decision":[121],"processes.":[122],"Importantly,":[123],"M-SAT":[124,148,196,218],"facilitates":[125],"development":[127],"more":[129,220],"interpretable":[130,223],"transparent":[132],"capable":[134],"making":[136],"decisions":[138],"dynamic":[140],"involving":[142],"spaces.":[145,229],"We":[146],"evaluate":[147],"on":[149,155],"challenging":[151],"ViZDoom":[152],"environments,":[153],"focusing":[154],"scenarios":[156],"observations,":[163],"such":[164],"as":[165],"Deadly":[166],"Corridor,":[167],"My":[168],"Way":[169],"Home":[170],"Death":[172],"Match.":[173],"Our":[174],"demonstrates":[176],"superior":[177],"compared":[179],"baseline":[181],"Transformers,":[183],"no":[185],"additional":[186],"data":[187],"or":[188],"computational":[190],"overheads.":[191],"Furthermore,":[192],"observe":[194],"that":[195,217],"does":[197],"not":[198],"require":[199],"positional":[200],"encoding":[201],"achieve":[203],"high":[204],"performance,":[205],"its":[207],"removal":[208],"occasionally":[209],"leading":[210],"further":[212],"improvements.":[213],"These":[214],"findings":[215],"suggest":[216],"enables":[219],"efficient":[221],"agent-based":[224]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}