{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001806932,0.0004075749,0.0003680458,0.0001686135,0.0004006702,0.001033274,0.001251994,0.0003082248,0.002158691],"category_scores_gemma":[0.0006684316,0.0004799337,0.0002004921,0.0009132266,0.0003039573,0.0008986203,0.000350191,0.0005996192,0.005164682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004623142,"about_ca_system_score_gemma":0.0004203235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001107521,"about_ca_topic_score_gemma":0.000007976217,"domain_scores_codex":[0.9960291,0.0006759097,0.0009218804,0.0007414324,0.00043902,0.001192645],"domain_scores_gemma":[0.9967949,0.001056736,0.000461151,0.00105523,0.0002809839,0.0003510384],"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":[0.000007986405,0.0001330118,0.0003583919,0.0001894692,0.00004393337,0.0000475619,0.004809656,0.8768471,0.001573134,0.03947332,0.007094546,0.06942185],"study_design_scores_gemma":[0.00008011486,0.0001534993,0.0003403723,0.0004150487,0.00004809782,0.0001136238,0.0009354578,0.9254158,0.01368771,0.002738267,0.05561188,0.0004600885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001551496,0.001952137,0.9404733,0.003109047,0.001180157,0.0006306543,0.000003822562,0.0001908616,0.05090855],"genre_scores_gemma":[0.7516473,0.001445168,0.1442313,0.0003540852,0.0003275668,0.000119454,0.00001012241,0.00005261944,0.1018124],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7962419,"threshold_uncertainty_score":0.9997652,"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."}}