{"id":"W2066471519","doi":"10.3166/ria.21.9-33","title":"Apprentissage actif dans les processus décisionnels de Markov partiellement observables L'algorithme MEDUSA","year":2007,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Physics; Philosophy","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":[0.002384518,0.001117255,0.001655564,0.0005799911,0.000895172,0.001949731,0.001577765,0.001970753,0.002471478],"category_scores_gemma":[0.007554416,0.0006901543,0.001136793,0.0004875408,0.002331516,0.002138299,0.001979074,0.002564156,0.0004612949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001477318,"about_ca_system_score_gemma":0.002333187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007393787,"about_ca_topic_score_gemma":0.007236946,"domain_scores_codex":[0.9986325,0.0005101023,0.00005257005,0.0003268574,0.0002626393,0.0002152991],"domain_scores_gemma":[0.9961505,0.002754678,0.0002121037,0.0002842866,0.0003597145,0.0002387982],"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":[0.0004069236,0.0001208354,0.001168531,0.0001173634,0.00007009695,0.0001536453,0.000266407,0.8859025,0.002623277,0.05444442,0.001096505,0.05362953],"study_design_scores_gemma":[0.00003020308,0.00004473489,0.00004742046,0.000006752201,0.000005439975,0.0000146097,0.00001483061,0.9898122,0.0008078468,0.008776938,0.0004332137,0.000005759024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04105917,0.000166727,0.9561324,0.0003492285,0.00003494947,0.00005268,0.00003224339,0.0006952955,0.001477308],"genre_scores_gemma":[0.6337594,0.0002293279,0.3601609,0.0002498233,0.0000571918,0.0002628656,0.000144093,0.0001359375,0.00500039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007393787,"threshold_uncertainty_score":0.01470149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07443563189771293,"score_gpt":0.3055678652788824,"score_spread":0.2311322333811695,"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."}}