{"id":"W2264982354","doi":"10.3166/ria.27.243-263","title":"Adaptation de la matrice de covariance pour l’apprentissage par renforcement direct","year":2013,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Adaptation (eye); Reinforcement learning; Covariance; Parameterized complexity; Humanities; Political science; Computer science; Psychology; Artificial intelligence; Mathematics; Philosophy; Algorithm; Neuroscience; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003422013,0.001368457,0.001617485,0.0004956106,0.0005688971,0.001482573,0.001302782,0.003055854,0.006611856],"category_scores_gemma":[0.01242038,0.0006673427,0.001292198,0.0004205165,0.001558646,0.001459969,0.001373701,0.00367246,0.001750063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001460388,"about_ca_system_score_gemma":0.00265241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02600619,"about_ca_topic_score_gemma":0.01932293,"domain_scores_codex":[0.9978862,0.0008883008,0.00008995988,0.0004806143,0.0004792757,0.000175581],"domain_scores_gemma":[0.9927102,0.005218906,0.0002065981,0.0005505909,0.001094921,0.0002187455],"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":[0.0004234938,0.0002031318,0.000714266,0.0001413359,0.0001344215,0.0001552931,0.0001818989,0.8201524,0.01549311,0.0213791,0.003169282,0.1378524],"study_design_scores_gemma":[0.00002376604,0.00005037642,0.0003390309,0.000008070872,0.000006548832,0.00002264745,0.000005904765,0.9958812,0.001763691,0.001203587,0.0006815315,0.00001363682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01820895,0.0002959595,0.9780806,0.0004215392,0.0001900296,0.0000866589,0.00004331456,0.000562049,0.002111012],"genre_scores_gemma":[0.6221566,0.0006779091,0.3428693,0.0005761361,0.0004382586,0.0007350295,0.0002509187,0.0005038168,0.03179208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02600619,"threshold_uncertainty_score":0.05170965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04328650558652317,"score_gpt":0.278600095215143,"score_spread":0.2353135896286198,"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."}}