{"id":"W6958632914","doi":"10.6084/m9.figshare.3085861","title":"Reinforcement Learning in a Nutshell","year":2016,"lang":"en","type":"other","venue":"Figshare","topic":"Peanut Plant Research Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Presentation (obstetrics); Control (management); Stability (learning theory)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001265992,0.0009868301,0.0008062806,0.0002869706,0.0002946808,0.001630849,0.001461172,0.001210396,0.01910054],"category_scores_gemma":[0.005382426,0.0004821932,0.0004485464,0.0002642497,0.001184554,0.003110013,0.002003363,0.00331264,0.00655996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000612964,"about_ca_system_score_gemma":0.001085807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001221377,"about_ca_topic_score_gemma":0.001795133,"domain_scores_codex":[0.9995673,0.0001459642,0.00003020613,0.000101982,0.0001299839,0.00002453161],"domain_scores_gemma":[0.9987716,0.0005437097,0.00006932685,0.0002857412,0.0002196119,0.000109985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002439075,0.0002174651,0.0007574278,0.0003826035,0.0002001297,0.0001237572,0.000216906,0.08417277,0.00468913,0.4261378,0.05511686,0.4277411],"study_design_scores_gemma":[0.0000982585,0.0001587701,0.000345235,0.0003115132,0.00005018558,0.0001379904,0.00004842228,0.2238318,0.002334269,0.6967147,0.07590821,0.0000606141],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004004997,0.001835031,0.9397727,0.006079119,0.0007616976,0.000122994,0.0002510857,0.002619721,0.04455271],"genre_scores_gemma":[0.2160937,0.003028645,0.6901438,0.003416153,0.0007576442,0.0005887981,0.0006581143,0.001099763,0.08421341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01910054,"threshold_uncertainty_score":0.06389767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04569544578629976,"score_gpt":0.2652384635416695,"score_spread":0.2195430177553697,"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."}}