{"id":"W2152469292","doi":"10.3166/ria.27.171-194","title":"Stratégies d’échantillonnage pour l’apprentissage par renforcement batch","year":2013,"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":"Psychology","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":[0.005274135,0.0014054,0.002008208,0.001067939,0.001558807,0.002939806,0.003559888,0.003249812,0.01506982],"category_scores_gemma":[0.02074962,0.0007408681,0.0009603414,0.0005856557,0.001750992,0.003118352,0.002155736,0.00317747,0.003322938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001819201,"about_ca_system_score_gemma":0.004193916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01076732,"about_ca_topic_score_gemma":0.009884753,"domain_scores_codex":[0.9954391,0.001829975,0.0002120674,0.0007562673,0.001250267,0.0005123355],"domain_scores_gemma":[0.9846705,0.009755468,0.0005658896,0.001490314,0.002706635,0.0008111756],"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":[0.0021076,0.0006407888,0.002398769,0.0004722652,0.0002092988,0.0008874345,0.0006749006,0.4971136,0.01772863,0.1160853,0.01959749,0.3420839],"study_design_scores_gemma":[0.0001317259,0.0001790105,0.0005893854,0.00003193995,0.00003084633,0.000132362,0.00006379616,0.9546283,0.005870114,0.03177375,0.006513411,0.00005530773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05587986,0.0008132286,0.9271196,0.00144703,0.0005241438,0.0004056669,0.0001397241,0.002045525,0.01162524],"genre_scores_gemma":[0.7097182,0.0005808637,0.2371596,0.0004362178,0.0003472005,0.0006566258,0.0003151781,0.0005162834,0.05026988],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01506982,"threshold_uncertainty_score":0.05041355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05199311426374947,"score_gpt":0.2708318065741388,"score_spread":0.2188386923103893,"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."}}