{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002945005,0.000340991,0.0005254187,0.0002039052,0.0004516656,0.0001164897,0.0007444819,0.0001465697,0.001428255],"category_scores_gemma":[0.001201046,0.0002344931,0.00003193997,0.00009086296,0.000962346,0.0001014639,0.0001366988,0.001064982,0.0001855055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002402976,"about_ca_system_score_gemma":0.0004946066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001520534,"about_ca_topic_score_gemma":0.0001358542,"domain_scores_codex":[0.9967949,0.0001545123,0.0009235309,0.0004436793,0.001068731,0.000614665],"domain_scores_gemma":[0.9948708,0.003843516,0.0006814955,0.0003770291,0.0001120005,0.0001151159],"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":[0.00000262931,0.00000876783,0.000005747826,0.0001624606,0.000003926873,0.00001076222,0.0005563882,0.00004417455,1.644494e-7,0.9560194,0.03388472,0.009300883],"study_design_scores_gemma":[0.00006227507,0.0006369398,0.00001273758,0.0002980497,0.000008921369,0.00001039521,0.0001720037,0.0011702,9.678351e-7,0.9671862,0.03019742,0.0002439184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002892618,0.0001692719,0.5757053,0.0005254929,0.0001609335,0.000968385,0.0001047539,0.0001155167,0.4222474],"genre_scores_gemma":[0.003588662,0.001607875,0.7999181,0.001729575,0.0001644336,0.0001562355,0.0001036592,0.00007754377,0.1926539],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2295935,"threshold_uncertainty_score":0.9994846,"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."}}