{"id":"W4315489024","doi":"10.1109/cdc51059.2022.9992565","title":"Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Linear-quadratic-Gaussian control; Reinforcement learning; Logarithm; Regret; Network packet; Bounded function; Control theory (sociology); Generalization; Controller (irrigation); Sampling (signal processing); Gaussian; Discrete mathematics; Mathematics; Computer science; Optimal control; Control (management); Mathematical optimization; Artificial intelligence; Mathematical analysis; Statistics; Telecommunications","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"],"consensus_categories":[],"category_scores_codex":[0.002163963,0.0004085483,0.0008878926,0.0003248076,0.000746449,0.0002626932,0.001227792,0.0001100811,0.00007363776],"category_scores_gemma":[0.0003130843,0.0003818832,0.0002654167,0.0004365857,0.0001018547,0.0002071686,0.0002074892,0.0005881175,0.000007674893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001483386,"about_ca_system_score_gemma":0.0002899303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003800192,"about_ca_topic_score_gemma":0.000007437155,"domain_scores_codex":[0.995978,0.0004731988,0.0009335377,0.0009005943,0.001029014,0.0006856489],"domain_scores_gemma":[0.9954773,0.002389525,0.0006777018,0.0007791547,0.0004450575,0.0002312759],"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":[0.001525379,0.0001360285,0.0001472533,0.0000315205,0.0001251074,0.00001215925,0.0001353383,0.7704754,0.002152676,0.05902041,0.0001418927,0.1660968],"study_design_scores_gemma":[0.009562808,0.001610507,0.00006420166,0.00009484644,0.00005614991,0.000006850825,0.0001669725,0.9658297,0.00002764783,0.0006444361,0.02155994,0.000375975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002312212,0.000467385,0.9929781,0.000665938,0.00129972,0.001765167,0.00003379037,0.000167948,0.0003097577],"genre_scores_gemma":[0.9928021,0.00002426068,0.004981845,0.0007090598,0.0001375242,0.0007954936,0.00001789069,0.00003418037,0.000497615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9904899,"threshold_uncertainty_score":0.9998633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03500695118355131,"score_gpt":0.2775513208392075,"score_spread":0.2425443696556562,"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."}}