{"id":"W4402423740","doi":"10.24908/iqurcp18060","title":"Reinforcement Learning for Jointly Optimal Coding and Control Policies for a Markovian System Controlled over a Communication Channel","year":2024,"lang":"en","type":"article","venue":"Inquiry Queen s Undergraduate Research Conference Proceedings","topic":"Stability and Control of Uncertain Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Coding (social sciences); Computer science; Channel (broadcasting); Markov process; Reinforcement; Control (management); Computer network; Artificial intelligence; Psychology; Mathematics; Social psychology; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001959986,0.0009217436,0.001122879,0.0005370145,0.0004822134,0.001005235,0.0008383084,0.001149588,0.00178233],"category_scores_gemma":[0.008361667,0.0004241853,0.0007047629,0.0003881,0.002307312,0.001240721,0.001203845,0.001942235,0.0001704222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002744491,"about_ca_system_score_gemma":0.00236338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01278915,"about_ca_topic_score_gemma":0.00684243,"domain_scores_codex":[0.9991059,0.0003170446,0.00003720355,0.000178297,0.0002279444,0.0001336019],"domain_scores_gemma":[0.995053,0.003920691,0.0004335527,0.0001396125,0.0003311909,0.0001220166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003498104,0.0000151162,0.0002513251,0.00003625546,0.00001469363,0.00003590364,0.00004765336,0.9643778,0.0004252575,0.03129321,0.0001757055,0.003292177],"study_design_scores_gemma":[0.000004033923,0.000008818975,0.00002754358,0.000003567058,0.000001924661,0.000002657674,0.000002836717,0.9943184,0.00007161669,0.005492844,0.00006357521,0.000002196356],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0274211,0.0003286423,0.9688606,0.0004413131,0.00003343088,0.00003864533,0.00003958594,0.000110273,0.002726423],"genre_scores_gemma":[0.9426579,0.0004200217,0.0533255,0.000113559,0.00004702582,0.0001845916,0.00009963459,0.0000548897,0.003097008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01278915,"threshold_uncertainty_score":0.02542943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05783002002300079,"score_gpt":0.3304231627302595,"score_spread":0.2725931427072587,"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."}}