{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003849354,0.0003638797,0.0007624858,0.0005300573,0.0005959457,0.001338738,0.0003842783,0.0002087342,0.000004207894],"category_scores_gemma":[0.0006605577,0.0003346413,0.0002041237,0.0003452792,0.0003420584,0.0006148539,0.0001016147,0.0006004085,0.00000567199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005451626,"about_ca_system_score_gemma":0.0001813837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001958306,"about_ca_topic_score_gemma":0.00001455853,"domain_scores_codex":[0.9970604,0.0001074472,0.0007371762,0.0005165216,0.0006014233,0.0009769995],"domain_scores_gemma":[0.9965174,0.001844384,0.0000962573,0.000209076,0.001098078,0.0002348087],"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":[0.005071139,0.00007136594,0.000382277,0.02165684,0.002196125,0.000007834799,0.02789361,0.01461984,0.02383868,0.8895312,0.008082913,0.006648161],"study_design_scores_gemma":[0.005565585,0.0004945172,0.00003440087,0.001611735,0.0000881748,0.00001226126,0.01083579,0.9712151,0.0003575003,0.004682874,0.004727106,0.0003749546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06638587,0.004745527,0.8850303,0.02011861,0.0008302192,0.01551745,0.00006771588,0.002274907,0.005029445],"genre_scores_gemma":[0.9937825,0.0005065608,0.0002873621,0.00002861935,0.0003329956,0.004393221,0.00002157918,0.0000824313,0.0005647433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9565952,"threshold_uncertainty_score":0.9999105,"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."}}