{"id":"W4307826006","doi":"10.36227/techrxiv.21387756","title":"Deep Q‑Learning Based Resource Management in IRS-Assisted VLC Systems","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Optical Wireless Communication Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Visible light communication; Computer science; Robustness (evolution); Wireless; Bandwidth (computing); Spectral efficiency; Radio frequency; Distributed computing; Algorithm; Real-time computing; Electronic engineering; Computer network; Telecommunications; Engineering; Electrical engineering; Light-emitting diode","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001294257,0.0005178339,0.0008633075,0.0002765924,0.0005926187,0.001041443,0.001190826,0.0008369033,0.002263915],"category_scores_gemma":[0.002176958,0.0002601931,0.0002578928,0.0004750315,0.0009267914,0.0009681627,0.000941913,0.0009557265,0.0002623201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001473447,"about_ca_system_score_gemma":0.00187564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01067185,"about_ca_topic_score_gemma":0.008498874,"domain_scores_codex":[0.9994597,0.0001553083,0.0000167792,0.00009177505,0.0001030641,0.0001734343],"domain_scores_gemma":[0.9991112,0.0005045623,0.0000923876,0.00004355686,0.0001789719,0.00006918646],"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":[0.0001243894,0.00008235984,0.0006705297,0.00004261825,0.00002036103,0.00008904059,0.00005045284,0.9322427,0.001925604,0.009526047,0.001680256,0.05354559],"study_design_scores_gemma":[0.000003494887,0.00001007531,0.00003319327,0.000001174829,0.000001319045,0.000004581542,0.00000364331,0.9985423,0.0001626915,0.001131713,0.0001041303,0.000001781415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07437544,0.001079634,0.9166028,0.0007826922,0.0001061005,0.00006395928,0.00006339586,0.0004746268,0.006451329],"genre_scores_gemma":[0.9682989,0.00015876,0.02881606,0.0001831456,0.00003612427,0.00003533234,0.00003199523,0.00002229894,0.002417438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01067185,"threshold_uncertainty_score":0.02121949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01969166094080505,"score_gpt":0.2380020906018059,"score_spread":0.2183104296610008,"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."}}