{"id":"W2101709153","doi":"10.1109/icsmc.1998.728123","title":"A new technique for reinforcement learning for control","year":2002,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Ball (mathematics); Control theory (sociology); Swing; Piecewise; Task (project management); Inverted pendulum; Control (management); Artificial intelligence; Nonlinear system; Mathematics; Engineering","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":[0.001034278,0.001030197,0.0008725521,0.000437603,0.000519976,0.0008168673,0.001407387,0.001156878,0.005198575],"category_scores_gemma":[0.002421544,0.0003971402,0.0008592767,0.0004758976,0.001660138,0.001404369,0.001440494,0.003157731,0.001183948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006937112,"about_ca_system_score_gemma":0.000568142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001261158,"about_ca_topic_score_gemma":0.001112224,"domain_scores_codex":[0.9993205,0.0001927629,0.00003740246,0.0001530884,0.000254876,0.00004130421],"domain_scores_gemma":[0.9994837,0.0002900648,0.00004218757,0.00007901838,0.00007598689,0.00002900561],"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":[0.0001212645,0.000114131,0.0002966938,0.000389871,0.0001428402,0.000173448,0.0002317234,0.2449843,0.01064326,0.4947752,0.006247566,0.2418797],"study_design_scores_gemma":[0.00009133053,0.0002000888,0.00009465975,0.00006323728,0.00004380837,0.0001639863,0.0000190434,0.7775903,0.003624154,0.1864616,0.03161765,0.00003010294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005329063,0.0002302689,0.9958467,0.0001573346,0.0001035019,0.00002481048,0.000009301321,0.0001420883,0.002953156],"genre_scores_gemma":[0.2813173,0.001384079,0.697959,0.0007571667,0.0005272303,0.0006394379,0.0000745936,0.0002148823,0.01712636],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005198575,"threshold_uncertainty_score":0.01739097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01849185421854255,"score_gpt":0.2495761896921465,"score_spread":0.2310843354736039,"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."}}