{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002531568,0.001054168,0.001589174,0.0003720967,0.000431165,0.0008458662,0.001349191,0.001247926,0.001234228],"category_scores_gemma":[0.005291544,0.0005210027,0.000485522,0.0003561635,0.001368187,0.0009800382,0.0009165565,0.001568178,0.00016007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001258911,"about_ca_system_score_gemma":0.001794882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006989977,"about_ca_topic_score_gemma":0.004597482,"domain_scores_codex":[0.9991062,0.0003228579,0.0000404794,0.000176612,0.000162343,0.0001914695],"domain_scores_gemma":[0.9967588,0.002284681,0.0003674981,0.0001228056,0.0002950354,0.0001711683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001347512,0.0001222236,0.001057328,0.000042207,0.00003247497,0.00008234921,0.00006719909,0.9789243,0.0009205662,0.00506065,0.000239653,0.01331631],"study_design_scores_gemma":[0.00001079136,0.00002657328,0.00006070787,0.000001756545,0.000004015153,0.000005064252,0.000003042781,0.9988021,0.000107518,0.0009493881,0.00002621332,0.000002862285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09361808,0.0003838397,0.9029695,0.000403131,0.00004532973,0.0001056978,0.00003276095,0.0002989846,0.002142795],"genre_scores_gemma":[0.9804527,0.00007510346,0.01831836,0.00008810874,0.00001710557,0.00008867023,0.0000210056,0.0000152661,0.0009237425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006989977,"threshold_uncertainty_score":0.01389861,"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."}}