{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007970952,0.0006654559,0.0006458496,0.0002019393,0.0003386574,0.0006059227,0.001327414,0.0009035058,0.002154443],"category_scores_gemma":[0.001376173,0.0003158552,0.0004075654,0.0001843652,0.0006861427,0.0008980698,0.001036822,0.001237363,0.0003557322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002558393,"about_ca_system_score_gemma":0.0009381737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001843991,"about_ca_topic_score_gemma":0.001361792,"domain_scores_codex":[0.9997073,0.00008461439,0.00001465274,0.0000791308,0.00008417029,0.00003019469],"domain_scores_gemma":[0.999606,0.0001469868,0.00006936531,0.00006605566,0.00007610796,0.00003556344],"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":[0.0001385787,0.0002628409,0.0007153862,0.0001885819,0.0001128443,0.0002592912,0.0002124884,0.7619792,0.01817202,0.05493947,0.002159013,0.1608603],"study_design_scores_gemma":[0.0000154384,0.0000655423,0.0000491666,0.000005122519,0.000006598612,0.00003369748,0.000004044285,0.9948754,0.00130817,0.003018584,0.0006110379,0.000007164788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008702135,0.00009142783,0.9889876,0.0001128502,0.00004120904,0.00003721816,0.000008316993,0.0004146191,0.001604496],"genre_scores_gemma":[0.8505517,0.0001567145,0.1455158,0.000128841,0.00004684496,0.0001695532,0.00003726345,0.00003783651,0.003355336],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002154443,"threshold_uncertainty_score":0.007207334,"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."}}