{"id":"W4319453072","doi":"10.1109/tac.2023.3243165","title":"An Online Model-Following Projection Mechanism Using Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Projection (relational algebra); Computer science; Control theory (sociology); Online model; Adaptive control; Adaptation (eye); Optimal control; Mathematical optimization; Control (management); Iterative learning control; Projection method; Horizon; Dykstra's projection algorithm; Artificial intelligence; Mathematics; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000653639,0.0002886744,0.0003491934,0.0005395313,0.0005634932,0.0002103992,0.0005544414,0.0001140939,0.000008557184],"category_scores_gemma":[0.00001947487,0.0002925986,0.000244888,0.0008552682,0.00002460069,0.0008205281,0.000004329411,0.0003131859,0.00005870903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002849547,"about_ca_system_score_gemma":0.0001747561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006459508,"about_ca_topic_score_gemma":0.00002671765,"domain_scores_codex":[0.9976476,0.0001962438,0.0004825613,0.0005391278,0.0005743912,0.0005600759],"domain_scores_gemma":[0.9988449,0.0001515445,0.0001715768,0.0006095506,0.00008505357,0.0001374116],"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":[0.00001065148,0.0001128134,0.000001770877,0.00001144783,0.0001021563,0.00001605004,0.0005408936,0.8705174,0.01295894,0.000892652,0.000001267282,0.1148339],"study_design_scores_gemma":[0.001605655,0.0003267764,0.00001468518,0.00005859285,0.00008824186,0.00001149961,0.0001386212,0.9961799,0.0006069586,0.0006694315,0.000007805723,0.000291855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06306045,0.00000350978,0.9325607,0.0001835484,0.0006477743,0.0008096278,0.000004309404,0.002706824,0.00002322577],"genre_scores_gemma":[0.9551929,0.000001654912,0.04412473,0.0002305575,0.00003250354,0.0001485151,0.000004109993,0.0000379179,0.000227135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8921325,"threshold_uncertainty_score":0.9999526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03278349811512623,"score_gpt":0.2848965783962839,"score_spread":0.2521130802811577,"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."}}