{"id":"W4296558883","doi":"10.1109/adconip55568.2022.9894150","title":"Meta-Reinforcement Learning for Adaptive Control of Second Order Systems","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Honeywell (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Leverage (statistics); Process (computing); Controller (irrigation); Meta learning (computer science); Key (lock); Artificial intelligence; Machine learning; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.000223243,0.000116786,0.0003620334,0.00007085876,0.00008310495,0.000008639615,0.00008246952,0.00002253645,0.0005417727],"category_scores_gemma":[0.00001833219,0.000108889,0.00009497888,0.0001200336,0.000006581602,0.00009764491,0.00001804969,0.00009081458,0.000002185721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009738667,"about_ca_system_score_gemma":0.00001259087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001769283,"about_ca_topic_score_gemma":0.000005153993,"domain_scores_codex":[0.999185,0.00004284078,0.0003395288,0.0001087868,0.0001582346,0.0001656279],"domain_scores_gemma":[0.9995191,0.0001299387,0.00009800175,0.0001151944,0.0001096791,0.0000281271],"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":[0.00002980375,0.00000392216,0.000006361498,0.00005801622,0.001117253,2.402236e-7,0.00009224105,0.9928617,0.00153735,0.00408373,0.000128393,0.0000809686],"study_design_scores_gemma":[0.001200456,0.0001420315,0.000001795952,0.00000231252,0.0002493965,0.000001934321,0.0004441747,0.9842891,0.0002063059,0.00001858052,0.01333106,0.0001128913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002110756,0.0009890688,0.9921136,0.000007516855,0.0002684881,0.0009744665,0.00001845161,0.0001586218,0.005258709],"genre_scores_gemma":[0.9924102,0.000001937896,0.001600538,0.00001716172,0.00002990974,0.001362376,0.00001628025,0.00003280025,0.004528782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9921991,"threshold_uncertainty_score":0.5932031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01809623477758406,"score_gpt":0.2089249018463832,"score_spread":0.1908286670687991,"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."}}