{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001847404,0.0005336753,0.0006630645,0.0004435401,0.0006596498,0.00131978,0.001288864,0.001954254,0.001785324],"category_scores_gemma":[0.003243256,0.0002389626,0.0004947149,0.0006671374,0.001527016,0.001212486,0.001152825,0.001751469,0.0001989643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162399,"about_ca_system_score_gemma":0.0009088802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006639342,"about_ca_topic_score_gemma":0.003039306,"domain_scores_codex":[0.9991028,0.0004444716,0.00003461554,0.000124516,0.0001994395,0.00009406399],"domain_scores_gemma":[0.9983559,0.001092425,0.0001038839,0.000153162,0.0001896294,0.0001049805],"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":[0.0001863976,0.0002792002,0.001538497,0.0001815275,0.00005871943,0.001365611,0.0002257804,0.7691661,0.001449064,0.1612466,0.002652707,0.06164977],"study_design_scores_gemma":[0.0000398846,0.00009462582,0.0002184278,0.00001594093,0.00001002473,0.0002047525,0.00004373658,0.9592314,0.0008700592,0.0349263,0.004330031,0.00001484411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07924312,0.003452896,0.8923436,0.001932075,0.0001168825,0.0002076631,0.00009982885,0.0005516128,0.0220524],"genre_scores_gemma":[0.8872135,0.001205483,0.1074028,0.0001330517,0.0000740602,0.0001531516,0.00004944457,0.00004167301,0.003726937],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006639342,"threshold_uncertainty_score":0.01320136,"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."}}