{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008628345,0.0007152515,0.0006311896,0.0002628387,0.0005853485,0.001668014,0.002295175,0.0003614101,0.009798909],"category_scores_gemma":[0.0002925218,0.0007848802,0.0003798507,0.001130693,0.0004853202,0.001957306,0.0009970115,0.0008239154,0.02683987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001958051,"about_ca_system_score_gemma":0.0002166603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007460593,"about_ca_topic_score_gemma":0.00002070306,"domain_scores_codex":[0.9944025,0.0002697365,0.001570048,0.001264119,0.0007701151,0.001723424],"domain_scores_gemma":[0.9959149,0.0004050531,0.0005817779,0.00209318,0.0005334381,0.0004716838],"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":[0.000005541291,0.0002271556,0.0003897577,0.0003694637,0.00009687133,0.00007878704,0.004055336,0.8012537,0.003120658,0.07645997,0.0251569,0.08878583],"study_design_scores_gemma":[0.0000893791,0.0003252882,0.0002009666,0.000638481,0.00004856541,0.00007590153,0.002350319,0.900871,0.03250007,0.003572871,0.05853492,0.0007922823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004526824,0.00269416,0.9339709,0.01217092,0.004648232,0.001185033,0.00000750887,0.0003016531,0.04049472],"genre_scores_gemma":[0.7318645,0.0011521,0.0240971,0.0003862457,0.0004810535,0.0001099121,0.00001935725,0.0000709158,0.2418188],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9098738,"threshold_uncertainty_score":0.9994602,"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."}}