{"id":"W2113710263","doi":"10.1109/icca.2003.1595047","title":"A Reinfrocement Learning Approach to Online Learning in Control","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Control (management); Online learning; Artificial intelligence; Multimedia","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":[0.001005381,0.0005203913,0.0007045742,0.000356933,0.0003807754,0.0006183013,0.001491448,0.0009778626,0.003436786],"category_scores_gemma":[0.002040972,0.000250868,0.0005570977,0.0003928418,0.001494075,0.001309295,0.0008286281,0.001751885,0.0004379082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007076143,"about_ca_system_score_gemma":0.0005728214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001997082,"about_ca_topic_score_gemma":0.001653338,"domain_scores_codex":[0.9995769,0.0001708215,0.00001720761,0.00007337111,0.0001280593,0.00003365745],"domain_scores_gemma":[0.9994767,0.0002938583,0.00003768855,0.0000754682,0.00009196324,0.00002438722],"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":[0.00007011652,0.00006784088,0.0002863952,0.0001431802,0.00005827083,0.0001241613,0.0001909851,0.5020033,0.004455443,0.3540281,0.001652003,0.1369202],"study_design_scores_gemma":[0.00001436308,0.00008610408,0.00004851375,0.000009846883,0.000005462124,0.00003228364,0.000007981736,0.9317622,0.0009679713,0.06385331,0.003203661,0.000008289029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002368879,0.0002611912,0.9950804,0.0001782656,0.00002776509,0.00001235799,0.000004733306,0.00008665465,0.001979797],"genre_scores_gemma":[0.5529656,0.0009701622,0.4297836,0.0004155758,0.0002356323,0.0001937747,0.00003959339,0.0001020891,0.0152939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003436786,"threshold_uncertainty_score":0.01149714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819162284227271,"score_gpt":0.2458991582055008,"score_spread":0.2277075353632281,"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."}}