{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003868595,0.0007119694,0.000613683,0.0002841487,0.0009147107,0.0007686316,0.002531992,0.0004801947,0.001548883],"category_scores_gemma":[0.0006981575,0.0007924455,0.000338113,0.001680226,0.0005352345,0.001021193,0.0009352744,0.0009816055,0.001125935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005788059,"about_ca_system_score_gemma":0.0003952509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003669622,"about_ca_topic_score_gemma":0.0001598358,"domain_scores_codex":[0.993311,0.0002947394,0.001812439,0.001342317,0.0009972706,0.002242242],"domain_scores_gemma":[0.9954654,0.001048259,0.0006799899,0.001658108,0.0004792389,0.0006689799],"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":[0.00003723975,0.000361834,0.002019848,0.0004213082,0.00006799369,0.0002312045,0.01437804,0.6118654,0.002769452,0.009421881,0.001911127,0.3565146],"study_design_scores_gemma":[0.0001037775,0.0003301811,0.0003504424,0.0007309818,0.00007517634,0.0001540839,0.007401623,0.7846776,0.1017547,0.0009852335,0.1027027,0.0007334587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01059149,0.003929059,0.964251,0.002988797,0.003431808,0.0008118743,0.00001139226,0.0002750314,0.01370952],"genre_scores_gemma":[0.7593006,0.001992852,0.1193164,0.0003008671,0.0009556827,0.00006779921,0.00002990176,0.0001201593,0.1179157],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8449346,"threshold_uncertainty_score":0.9996518,"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."}}