{"id":"W4401011551","doi":"10.1016/b978-0-443-24010-2.00008-1","title":"Reinforcement learning","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement; Reinforcement learning; Psychology; Computer science; Artificial intelligence; Social psychology","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001957278,0.0003692186,0.0003390092,0.0002050684,0.00004020303,0.00007088637,0.0001515319,0.0002812614,0.0003650855],"category_scores_gemma":[0.000009966463,0.0003713132,0.0001988713,0.00001322465,0.00002128848,0.00002530726,0.00005627953,0.0008808746,0.0008220301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001132608,"about_ca_system_score_gemma":0.00001523325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.758562e-8,"about_ca_topic_score_gemma":3.923442e-7,"domain_scores_codex":[0.9989223,0.000006246697,0.00035616,0.0002270337,0.0002516665,0.0002365976],"domain_scores_gemma":[0.999468,0.00005280216,0.00002984302,0.0003174395,0.00003026839,0.0001015956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[9.186625e-7,1.745033e-7,1.470423e-7,0.0002747053,0.00009775175,0.00001793884,0.0000740414,0.6459557,0.00001659729,0.006578848,0.0001341412,0.346849],"study_design_scores_gemma":[0.00007784196,0.00001576194,2.763801e-7,0.0003652994,0.00004995273,0.000004573338,0.000001549234,0.1248472,0.00004019137,0.003718892,0.8705426,0.0003358587],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001335549,0.002834238,0.001533107,0.000006904284,0.0009615315,0.0001768973,0.000002517299,0.001076205,0.9933953],"genre_scores_gemma":[0.001596587,0.0002268019,0.001268704,0.00001244981,0.000416614,0.00001952383,0.00002417793,0.0002200302,0.9962151],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8704085,"threshold_uncertainty_score":0.999956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0162767702361299,"score_gpt":0.2502340135081798,"score_spread":0.2339572432720499,"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."}}