{"id":"W2806832624","doi":"10.1109/jas.2018.7511144","title":"Parallel reinforcement learning: a framework and case study","year":2018,"lang":"en","type":"article","venue":"IEEE/CAA Journal of Automatica Sinica","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Markov chain; Action learning; Action (physics); Markov decision process; Markov process; Cooperative learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005976137,0.0001608716,0.0003774576,0.0001341007,0.0001276602,0.00009936839,0.0001232636,0.00009489168,0.00009586495],"category_scores_gemma":[0.0001785545,0.0001326651,0.00008919198,0.0001504424,0.00006238859,0.0001413659,0.0000163253,0.0004248094,0.00004736201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004795929,"about_ca_system_score_gemma":0.00002889172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001236079,"about_ca_topic_score_gemma":0.000009608929,"domain_scores_codex":[0.9984959,0.0001071,0.0007933528,0.0001015861,0.0002903336,0.0002117562],"domain_scores_gemma":[0.9990665,0.0002170936,0.0002217375,0.0001935343,0.0001191488,0.0001820125],"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":[0.001726446,0.002987267,0.01332747,0.001671416,0.01256905,0.03571418,0.1715203,0.5018925,0.01716262,0.001426623,0.04284885,0.1971533],"study_design_scores_gemma":[0.004892516,0.006392729,0.001504906,0.0005291399,0.0003353542,0.021165,0.01240569,0.9325366,0.0003725812,0.000325156,0.0189051,0.0006352388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760475,0.0002265431,0.02076161,0.0001030548,0.001099721,0.0002417026,2.741672e-7,0.0001609475,0.001358668],"genre_scores_gemma":[0.9978276,0.00002420253,0.001483671,0.00004843676,0.0004533716,0.000006777056,4.949679e-8,0.00002574952,0.0001301299],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4306441,"threshold_uncertainty_score":0.5409927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460365057919548,"score_gpt":0.2757493008760759,"score_spread":0.2611456502968804,"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."}}