{"id":"W7123243466","doi":"","title":"Bridging control and reinforcement learning with partial model knowledge","year":2025,"lang":"en","type":"other","venue":"cIRcle (University of British Columbia)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Bridging (networking); Estimator; Nonlinear system; Robustness (evolution); Artificial neural network; Adaptive control; Convergence (economics); Domain knowledge; Sample (material)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002663828,0.001258551,0.001350691,0.0005393527,0.0003682849,0.001759681,0.001697804,0.001460508,0.001805411],"category_scores_gemma":[0.007466684,0.0008008993,0.0008992425,0.0004826537,0.002988828,0.002757001,0.002918464,0.002903734,0.0003305886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011946,"about_ca_system_score_gemma":0.001759121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002215161,"about_ca_topic_score_gemma":0.001414381,"domain_scores_codex":[0.9986632,0.0004477118,0.00007229998,0.0003050845,0.000394189,0.000117569],"domain_scores_gemma":[0.9954001,0.003260979,0.0003597333,0.000566245,0.0003022834,0.0001106996],"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":[0.00005390538,0.0000559552,0.0004479516,0.0002083189,0.00006548049,0.00009261472,0.0001507,0.7978988,0.001745629,0.1514275,0.0004972233,0.04735591],"study_design_scores_gemma":[0.000008920343,0.0000445958,0.00006175145,0.00002428395,0.000009462487,0.00001811992,0.00000848555,0.9477423,0.0007635696,0.0502131,0.001094496,0.00001084444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003947461,0.0003097116,0.9936566,0.0002871072,0.00002194922,0.00001525134,0.000009758252,0.00009652133,0.001655719],"genre_scores_gemma":[0.7320079,0.001532191,0.2611964,0.0004457179,0.0002226148,0.0002463893,0.0000788908,0.0001207122,0.004149252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002663828,"threshold_uncertainty_score":0.0140878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006442096113262501,"score_gpt":0.1788431210491139,"score_spread":0.1724010249358514,"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."}}