{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002699052,0.0006182677,0.0007978308,0.0002556498,0.000230436,0.0009489771,0.0007097617,0.0008363043,0.01195436],"category_scores_gemma":[0.0007684057,0.0002285293,0.0003233184,0.0005788736,0.0008409759,0.001087492,0.0006589681,0.001421135,0.002042847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007561446,"about_ca_system_score_gemma":0.0003852447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00236691,"about_ca_topic_score_gemma":0.002521227,"domain_scores_codex":[0.9998523,0.0000418357,0.000006575748,0.00002675185,0.00006182498,0.00001064539],"domain_scores_gemma":[0.9998741,0.00006709187,0.000008218869,0.00002056018,0.00002449406,0.000005608343],"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":[0.00003202995,0.00004375913,0.00007709063,0.0002566825,0.00002602326,0.00005019848,0.00006329134,0.1580525,0.001725932,0.5467755,0.03089084,0.2620062],"study_design_scores_gemma":[0.00001392917,0.00003260439,0.0001767371,0.00007628622,0.0000100757,0.00005185382,0.00002428748,0.4641359,0.0007625789,0.4874898,0.04720635,0.00001965928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00323383,0.0241381,0.8629669,0.001273581,0.001553512,0.00003971724,0.0001202855,0.0004866892,0.1061874],"genre_scores_gemma":[0.3761667,0.02847907,0.2715671,0.0008445534,0.002492212,0.0003440327,0.0004460353,0.0004293314,0.319231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01195436,"threshold_uncertainty_score":0.03999132,"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."}}