{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008334296,0.0006112957,0.0005701269,0.000429242,0.0003135866,0.0007298047,0.0008817288,0.0009273121,0.00286102],"category_scores_gemma":[0.003161807,0.0002353372,0.0003100957,0.0003355175,0.0008390572,0.0008965326,0.001397248,0.001434502,0.0003761766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006822174,"about_ca_system_score_gemma":0.0008576048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003250998,"about_ca_topic_score_gemma":0.003273505,"domain_scores_codex":[0.9996131,0.0001377913,0.00001996231,0.00007120478,0.0001079596,0.00004999282],"domain_scores_gemma":[0.9990989,0.0005397359,0.00007763125,0.00007039164,0.000147956,0.0000653697],"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":[0.0001966841,0.0002053152,0.002580043,0.000226947,0.0001131336,0.0001662205,0.0001195402,0.7108754,0.003340275,0.06218705,0.004919316,0.2150701],"study_design_scores_gemma":[0.00001690124,0.00007464547,0.0001724702,0.0000280147,0.00001140669,0.00003917562,0.00001378396,0.9729926,0.0008018378,0.02253458,0.003306523,0.000008094259],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04408945,0.005165633,0.9195495,0.002211467,0.0003518215,0.00009151436,0.00008393426,0.001144718,0.02731195],"genre_scores_gemma":[0.9204552,0.001766637,0.06936482,0.0005865912,0.0001243429,0.0000832006,0.00008214131,0.00007191436,0.007465166],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003250998,"threshold_uncertainty_score":0.009571075,"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."}}