{"id":"W275349574","doi":"10.1007/978-1-4614-7428-9_3","title":"Statistical Reinforcement Learning","year":2013,"lang":"en","type":"book-chapter","venue":"Statistics in the health sciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Sequence (biology); Machine learning; Reinforcement; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009427421,0.0009479586,0.0008566753,0.0005836739,0.000292025,0.001319669,0.0009355525,0.0008849457,0.01524709],"category_scores_gemma":[0.003287502,0.0003687998,0.0004455844,0.001010845,0.001188885,0.001226879,0.0007690705,0.00269407,0.005115872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009836063,"about_ca_system_score_gemma":0.0009138928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001467148,"about_ca_topic_score_gemma":0.002253369,"domain_scores_codex":[0.9996607,0.0001094826,0.00001487453,0.00007860746,0.0001194448,0.00001685194],"domain_scores_gemma":[0.9989389,0.0007936945,0.00002929026,0.0001026284,0.000106413,0.00002911478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002451594,0.00007597693,0.0002230203,0.0002462127,0.00004851189,0.0000507205,0.00008544719,0.04027006,0.0007988131,0.5227569,0.07836745,0.3570525],"study_design_scores_gemma":[0.00001132601,0.00002957481,0.0002516132,0.0001145772,0.00001541847,0.00007644429,0.00001802487,0.09736302,0.0007832502,0.7906008,0.1107118,0.00002414157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001539584,0.01541954,0.8926371,0.002669489,0.0009205017,0.00004186387,0.0003059234,0.001001898,0.08546419],"genre_scores_gemma":[0.176416,0.03265905,0.504004,0.002367812,0.002869494,0.0004630581,0.001678208,0.001278338,0.2782641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01524709,"threshold_uncertainty_score":0.05100656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2260064450045037,"score_gpt":0.4697251423898163,"score_spread":0.2437186973853127,"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."}}