{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008894269,0.00004983019,0.00005714964,0.00002673148,0.0001559554,0.0000332053,0.0002252297,0.00002441809,0.0000547097],"category_scores_gemma":[0.00001595528,0.0000443648,0.00005149368,0.00008419176,0.000005233094,0.0001318284,0.00002340728,0.00003152366,0.00001638313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000176461,"about_ca_system_score_gemma":0.00001471097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008528585,"about_ca_topic_score_gemma":6.753859e-7,"domain_scores_codex":[0.9995506,0.000003760603,0.0001061248,0.0001472517,0.00005563246,0.000136586],"domain_scores_gemma":[0.9996273,0.00008821012,0.00003275972,0.0001530191,0.00004928066,0.00004945505],"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":[0.000002399178,0.00002585683,0.00001026134,0.000007036893,0.00001028203,8.744713e-8,0.0000649974,0.006486853,0.002297288,0.9036456,0.05319038,0.03425898],"study_design_scores_gemma":[0.0004216035,0.0001076201,0.00001060477,0.000002297677,0.000002190895,0.000002104397,0.000003021089,0.8090583,0.0007275105,0.00765749,0.1819469,0.00006037367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[9.426371e-7,0.00003462244,0.9922621,0.003851661,0.00002666169,0.0009425313,5.482456e-7,0.0001256755,0.002755251],"genre_scores_gemma":[0.08745112,0.000005179823,0.8820688,0.0003785497,0.00009610074,0.001347072,0.000002439049,0.000004536838,0.02864623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8959881,"threshold_uncertainty_score":0.1809144,"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."}}