{"id":"https://openalex.org/W7125945319","doi":"https://doi.org/10.1049/cit2.70100","title":"TNCOA: Efficient Exploration via Observation\u2010Action Constraint on Trajectory\u2010Based Intrinsic Reward","display_name":"TNCOA: Efficient Exploration via Observation\u2010Action Constraint on Trajectory\u2010Based Intrinsic Reward","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125945319","doi":"https://doi.org/10.1049/cit2.70100"},"language":"en","primary_location":{"id":"doi:10.1049/cit2.70100","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70100","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70100","source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102428783","display_name":"Jingxiang Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210146529","display_name":"Autonomous Healthcare","ror":"https://ror.org/04kf58w92","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210146529"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jingxiang Ma","raw_affiliation_strings":["School of Automation Beijing Institute of Technology  Beijing China","State Key Laboratory of Autonomous Intelligent Unmanned System  Beijing China"],"raw_orcid":"https://orcid.org/0009-0009-2139-4102","affiliations":[{"raw_affiliation_string":"School of Automation Beijing Institute of Technology  Beijing China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"State Key Laboratory of Autonomous Intelligent Unmanned System  Beijing China","institution_ids":["https://openalex.org/I4210146529"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongbin Ma","orcid":"https://orcid.org/0000-0002-5734-3157"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210146529","display_name":"Autonomous Healthcare","ror":"https://ror.org/04kf58w92","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210146529"]},{"id":"https://openalex.org/I4210165204","display_name":"Zhuhai Institute of Advanced Technology","ror":"https://ror.org/05r1mzq61","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761","https://openalex.org/I4210165204"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Hongbin Ma","raw_affiliation_strings":["Beijing Institute of Technology  Zhuhai China","School of Automation Beijing Institute of Technology  Beijing China","State Key Laboratory of Autonomous Intelligent Unmanned System  Beijing China"],"raw_orcid":"https://orcid.org/0000-0002-5734-3157","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology  Zhuhai China","institution_ids":["https://openalex.org/I4210165204","https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Automation Beijing Institute of Technology  Beijing China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"State Key Laboratory of Autonomous Intelligent Unmanned System  Beijing China","institution_ids":["https://openalex.org/I4210146529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124118350","display_name":"Youzhi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Youzhi Zhang","raw_affiliation_strings":["Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences  Hong Kong China"],"raw_orcid":"https://orcid.org/0000-0002-2984-734X","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences  Hong Kong China","institution_ids":["https://openalex.org/I4210121405"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124118350"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4210121405","https://openalex.org/I4210146529","https://openalex.org/I4210165204"],"apc_list":{"value":2200,"currency":"USD","value_usd":2200},"apc_paid":{"value":2200,"currency":"USD","value_usd":2200},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10128683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"2","first_page":"411","last_page":"427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8169000148773193,"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":0.8169000148773193,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.024900000542402267,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01979999989271164,"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/novelty","display_name":"Novelty","score":0.8664000034332275},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7727000117301941},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.554099977016449},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5532000064849854},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.447299987077713},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8664000034332275},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7727000117301941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610000133514404},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.554099977016449},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112000107765198},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2777798563","wikidata":"https://www.wikidata.org/wiki/Q7603916","display_name":"State vector","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1049/cit2.70100","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70100","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70100","source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:26def0299d5d4640b6d762b0fe10993d","is_oa":true,"landing_page_url":"https://doaj.org/article/26def0299d5d4640b6d762b0fe10993d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CAAI Transactions on Intelligence Technology, Vol 11, Iss 2, Pp 411-427 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1049/cit2.70100","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70100","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70100","source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2826489423","display_name":null,"funder_award_id":"62473052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125945319.pdf","grobid_xml":"https://content.openalex.org/works/W7125945319.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2144913588","https://openalex.org/W2963523627","https://openalex.org/W3012544020","https://openalex.org/W3037694644","https://openalex.org/W3153727940","https://openalex.org/W4206547457","https://openalex.org/W4319165238","https://openalex.org/W4404146799"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Efficient":[1],"exploration":[2,143],"is":[3,194],"critical":[4],"in":[5,12,43,55,138,148,168,187],"handling":[6],"sparse":[7,158],"rewards":[8],"and":[9,39,107,115,157,171,183],"partial":[10],"observability":[11],"deep":[13],"reinforcement":[14],"learning.":[15],"However,":[16],"most":[17],"existing":[18],"intrinsic":[19],"reward":[20],"methods":[21],"based":[22],"on":[23,26,97,130,179],"novelty":[24,38,76,81,109,118],"rely":[25],"single\u2010step":[27],"observations":[28,88],"or":[29],"Euclidean":[30],"distances.":[31],"These":[32],"approaches":[33],"struggle":[34],"to":[35,64,110,141],"capture":[36],"trajectory\u2010level":[37,75],"often":[40],"perform":[41],"poorly":[42],"partially":[44],"observable":[45],"settings.":[46],"Moreover,":[47],"they":[48],"typically":[49],"ignore":[50],"the":[51,80,93,102,121,149],"role":[52],"of":[53,82],"actions":[54,62,106],"driving":[56],"observation":[57],"changes,":[58],"as":[59],"not":[60],"all":[61],"lead":[63],"meaningful":[65,98],"state":[66,84,139],"transitions.":[67],"To":[68,95],"overcome":[69],"these":[70],"limitations,":[71],"we":[72,100,125],"propose":[73],"a":[74,83,127],"measure":[77],"that":[78,136,162],"estimates":[79],"by":[85,120,153],"comparing":[86],"current":[87],"with":[89],"past":[90],"ones":[91],"along":[92],"trajectory.":[94],"focus":[96],"exploration,":[99],"incorporate":[101],"mutual":[103],"information":[104],"between":[105],"trajectory":[108],"filter":[111],"out":[112],"random":[113],"fluctuations":[114],"retain":[116],"only":[117,134],"caused":[119],"agent's":[122],"actions.":[123],"Additionally,":[124],"introduce":[126],"first\u2010visit":[128],"constraint":[129],"observation\u2013action":[131],"pairs,":[132],"rewarding":[133],"interactions":[135,156],"result":[137],"transitions":[140],"enhance":[142],"efficiency.":[144],"We":[145],"conducted":[146],"experiments":[147],"MiniGrid\u2010ObstructedMaze":[150],"environment":[151],"characterised":[152],"complex":[154],"object":[155],"rewards.":[159],"Results":[160],"demonstrate":[161],"our":[163],"method":[164],"achieves":[165],"state\u2010of\u2010the\u2010art":[166],"performance":[167,186],"convergence":[169],"speed":[170],"average":[172],"returns.":[173],"Furthermore,":[174],"it":[175],"shows":[176],"strong":[177],"generalisation":[178],"high\u2010dimensional":[180],"Atari":[181],"benchmarks":[182],"demonstrates":[184],"robust":[185],"more":[188],"challenging":[189],"MiniGrid":[190],"variants.":[191],"Implementation":[192],"code":[193],"available":[195],"at:":[196],"https://github.com/MurrayMa0816/TNCOA":[197],".":[198]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-29T00:00:00"}