{"id":"W2906153113","doi":"10.1109/tvt.2018.2888826","title":"Sensing, Probing, and Transmitting Policy for Energy Harvesting Cognitive Radio With Two-Stage After-State Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Cognitive Radio Networks and Spectrum Sensing","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Cognitive radio; Fading; Transmitter; Markov decision process; Channel (broadcasting); Transmission (telecommunications); Computer science; Q-learning; Throughput; Power control; Bellman equation; Energy (signal processing); Markov process; Energy harvesting; Optimization problem; Electronic engineering; Transmitter power output; Channel state information; Wireless; Telecommunications; Power (physics); Mathematical optimization; Engineering; Algorithm; Artificial intelligence; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002334167,0.0003170547,0.0003136933,0.0006862809,0.0007413531,0.0001585244,0.0001780794,0.0001432708,0.000003207027],"category_scores_gemma":[0.00002100457,0.0003015593,0.00008647925,0.0009355215,0.0004210031,0.0002792949,0.000007570972,0.0004312401,0.000002560386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009871971,"about_ca_system_score_gemma":0.0001110719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001873384,"about_ca_topic_score_gemma":0.0005019481,"domain_scores_codex":[0.9980596,0.0000765029,0.0003099642,0.0007130416,0.000187266,0.0006536299],"domain_scores_gemma":[0.9990388,0.0001695504,0.0001548523,0.0002764372,0.0002551248,0.0001052906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002557931,0.00007086878,0.00004792327,0.00004694687,0.0002678353,0.0001721198,0.001729047,0.02746557,0.006341645,0.004952452,0.000001991738,0.9586478],"study_design_scores_gemma":[0.002373972,0.002032654,0.00002571211,0.0005071411,0.00008145101,0.0004986559,0.0002537415,0.8393204,0.1517355,0.0007598641,0.001816256,0.0005946373],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1195189,0.0000738365,0.8786247,0.000620597,0.0000898699,0.0003576886,0.000003056663,0.0005071907,0.0002041818],"genre_scores_gemma":[0.9761972,0.00004028633,0.02279737,0.0002651382,0.00009485825,0.00005428709,0.00000164471,0.0000434764,0.0005056701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9580532,"threshold_uncertainty_score":0.9999437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007688865532782587,"score_gpt":0.2314373227270143,"score_spread":0.2237484571942318,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}