{"id":"W7124132313","doi":"10.65109/rxps5681","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","year":2016,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Representation (politics); Set (abstract data type); Benchmark (surveying); Strengths and weaknesses; Control (management); Key (lock)","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":[0.001061486,0.001049674,0.0008246657,0.0003276093,0.0003420715,0.001045507,0.001791259,0.0008862181,0.003734396],"category_scores_gemma":[0.002888554,0.0003424227,0.0004699545,0.0001897806,0.0009610988,0.001123545,0.001379721,0.001562581,0.0004389029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009588475,"about_ca_system_score_gemma":0.001019732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007460523,"about_ca_topic_score_gemma":0.007793696,"domain_scores_codex":[0.9995191,0.0001271128,0.00003044107,0.0001044951,0.0001366604,0.00008225402],"domain_scores_gemma":[0.998989,0.000554215,0.00009820014,0.0001223877,0.0001505999,0.00008544103],"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":[0.0001815566,0.0001258345,0.0006778198,0.0001374436,0.00005227069,0.0000460406,0.00006182561,0.8935911,0.001875905,0.01938612,0.001201975,0.08266217],"study_design_scores_gemma":[0.0000116738,0.00003512881,0.00004731897,0.000005568031,0.000003140812,0.000003679917,0.000002846556,0.9966989,0.000276921,0.002647674,0.0002642472,0.00000289822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0970965,0.001147836,0.8771294,0.0004879858,0.0001416387,0.000164453,0.0001137621,0.001125935,0.02259251],"genre_scores_gemma":[0.937328,0.0002452297,0.05897277,0.0001112245,0.00003370858,0.0001002106,0.00009445893,0.00006251076,0.003051769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007460523,"threshold_uncertainty_score":0.01483423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03731863179792241,"score_gpt":0.2776351405234208,"score_spread":0.2403165087254983,"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."}}