{"id":"https://openalex.org/W7125942982","doi":"https://doi.org/10.1109/smc58881.2025.11342671","title":"Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain","display_name":"Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125942982","doi":"https://doi.org/10.1109/smc58881.2025.11342671"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076234373","display_name":"Dimitris J. Panagopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitris Panagopoulos","raw_affiliation_strings":["Cranfield University,Faculty of Engineering and Applied Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cranfield University,Faculty of Engineering and Applied Science,UK","institution_ids":["https://openalex.org/I82284825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065156490","display_name":"Adolfo Perrusqu\u00eda","orcid":"https://orcid.org/0000-0003-2290-1160"},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adolfo Perrusqu\u00eda","raw_affiliation_strings":["Cranfield University,Faculty of Engineering and Applied Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cranfield University,Faculty of Engineering and Applied Science,UK","institution_ids":["https://openalex.org/I82284825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085188653","display_name":"Weisi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Weisi Guo","raw_affiliation_strings":["Cranfield University,Faculty of Engineering and Applied Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cranfield University,Faculty of Engineering and Applied Science,UK","institution_ids":["https://openalex.org/I82284825"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82284825"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6564075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5655","last_page":"5660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20669999718666077,"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":0.20669999718666077,"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/T13553","display_name":"Age of Information Optimization","score":0.18459999561309814,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.058800000697374344,"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":0.7858999967575073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6959999799728394},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6244000196456909},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6047000288963318},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4912000000476837},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.45559999346733093},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4185999929904938},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.40380001068115234}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7858999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156000137329102},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6959999799728394},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6244000196456909},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":11,"referenced_works":["https://openalex.org/W2765733960","https://openalex.org/W2963523627","https://openalex.org/W4206149971","https://openalex.org/W4206530644","https://openalex.org/W4214717370","https://openalex.org/W4220747123","https://openalex.org/W4318603619","https://openalex.org/W4402145986","https://openalex.org/W4406613090","https://openalex.org/W4406810538","https://openalex.org/W4407108822"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"systems":[1],"operating":[2],"in":[3,98,134,151],"high-stakes":[4],"search-and-rescue":[5],"(SAR)":[6],"missions":[7],"must":[8],"continuously":[9],"gather":[10],"mission-critical":[11],"information":[12,103],"while":[13,140],"flexibly":[14],"adapting":[15],"to":[16,80,96,109,144],"shifting":[17],"operational":[18],"priorities.":[19],"We":[20],"propose":[21],"CA-MIQ":[22,43,112],"(Context-Aware":[23],"Max-Information":[24],"Q-learning),":[25],"a":[26,45,83,87,123],"lightweight":[27],"dual-critic":[28],"reinforcement":[29],"learning":[30],"(RL)":[31],"framework":[32],"that":[33,56],"dynamically":[34],"adjusts":[35],"its":[36],"exploration":[37,71],"strategy":[38],"whenever":[39],"mission":[40],"priorities":[41],"change.":[42],"pairs":[44],"standard":[46],"extrinsic":[47],"critic":[48,55,75],"for":[49],"task":[50],"reward":[51],"with":[52,155],"an":[53],"intrinsic":[54],"fuses":[57],"state-novelty,":[58],"information-location":[59],"awareness,":[60],"and":[61,73,127],"real-time":[62],"priority":[63,84,100,125],"alignment.":[64],"A":[65],"built-in":[66],"shift":[67,126],"detector":[68],"triggers":[69],"transient":[70],"boosts":[72],"selective":[74],"resets,":[76],"allowing":[77],"the":[78,99,105],"agent":[79,106],"re-focus":[81],"after":[82,122],"revision.":[85],"In":[86],"simulated":[88],"SAR":[89],"grid-world,":[90],"where":[91],"experiments":[92],"specifically":[93],"test":[94],"adaptation":[95],"changes":[97],"order":[101],"of":[102],"types":[104],"is":[107],"expected":[108],"focus":[110],"on,":[111],"achieves":[113],"nearly":[114],"four":[115],"times":[116,131],"higher":[117],"mission-success":[118],"rates":[119],"than":[120,129],"baselines":[121],"single":[124],"more":[128],"three":[130],"better":[132],"performance":[133],"multiple-shift":[135],"scenarios,":[136],"achieving":[137],"100%":[138],"recovery":[139],"baseline":[141],"methods":[142],"fail":[143],"adapt.":[145],"These":[146],"results":[147],"highlight":[148],"CA-MIQ\u2019s":[149],"effectiveness":[150],"any":[152],"discrete":[153],"environment":[154],"piecewise-stationary":[156],"information-value":[157],"distributions.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}