{"id":"W4383560595","doi":"10.54254/2755-2721/5/20230668","title":"Applications of deep reinforcement learning — Alphago","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Deep learning; Field (mathematics); Computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001227012,0.00008564454,0.00009814464,0.0001581331,0.00007491288,0.00003780409,0.0001942843,0.00002660667,0.000004055488],"category_scores_gemma":[0.00001043032,0.00009479976,0.00002173523,0.0004914384,0.00001530027,0.00008349,0.0001530025,0.00009630742,0.00003377796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001307955,"about_ca_system_score_gemma":0.00001381262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001196562,"about_ca_topic_score_gemma":2.929806e-8,"domain_scores_codex":[0.99927,0.000003781963,0.0001972715,0.0001579141,0.0002210268,0.0001500112],"domain_scores_gemma":[0.9995943,0.0001460205,0.00006277598,0.0001123099,0.00003807102,0.00004651894],"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":[4.695921e-7,0.000001747559,0.0000269584,0.00002378159,0.00001110127,3.508039e-7,0.0001647193,0.7701821,0.0001912982,0.2219517,0.000007543855,0.007438314],"study_design_scores_gemma":[0.000147416,0.00001600887,0.001027192,0.000006140591,0.000002895517,0.000002059129,0.00002643555,0.9958897,0.0001157947,0.001143372,0.001530023,0.00009294067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007940684,0.00002311171,0.997235,0.0000478247,0.00003455556,0.0001290724,9.276226e-8,0.0002833999,0.0014529],"genre_scores_gemma":[0.9595425,0.00001042842,0.04022638,0.00002587328,0.00002451593,0.00005004013,0.00002119776,0.000008461972,0.00009058635],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9587485,"threshold_uncertainty_score":0.3865822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006777116084209396,"score_gpt":0.212453352432577,"score_spread":0.2056762363483677,"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."}}