{"id":"W4399828170","doi":"10.1007/978-3-031-54071-4_24","title":"Reinforcement Learning for Networked Control and Optimal Quantization","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Reinforcement; Quantization (signal processing); Computer science; Control (management); Artificial intelligence; Psychology; Computer vision; Social psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00134268,0.0008241998,0.001476964,0.0003333997,0.0002936187,0.001248384,0.0008297256,0.0006085093,0.000009374172],"category_scores_gemma":[0.00007174827,0.000776116,0.0004100042,0.00008639063,0.00007229317,0.0003777152,0.0001413783,0.0005528533,0.000207061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002832697,"about_ca_system_score_gemma":0.000174217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006973177,"about_ca_topic_score_gemma":0.000007721713,"domain_scores_codex":[0.9956787,0.000127107,0.001415205,0.001264314,0.000730033,0.0007846586],"domain_scores_gemma":[0.996883,0.0005683672,0.0009557589,0.000862387,0.0004500384,0.0002804202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001237275,0.000009227027,0.00001421098,0.0006488175,0.001120929,0.00004563691,0.0001198155,0.23171,0.0001237465,0.7600333,0.002962467,0.003088151],"study_design_scores_gemma":[0.003664135,0.0002385444,0.000002746296,0.0007392339,0.0002876952,0.0000328589,0.00001419975,0.6935874,7.534134e-7,0.000443991,0.3004621,0.000526417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000003536713,0.01134403,0.9392121,0.0004090842,0.003936356,0.005087378,0.0001052793,0.0006732931,0.03922891],"genre_scores_gemma":[0.7555603,0.00006803072,0.0001770472,0.0001316855,0.001383028,0.0007559815,0.0001528913,0.0001372926,0.2416337],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9390351,"threshold_uncertainty_score":0.9997884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01420318871499867,"score_gpt":0.2286332187848622,"score_spread":0.2144300300698635,"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."}}