{"id":"W2190606234","doi":"10.5555/2936924.2936996","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","year":2016,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Benchmark (surveying); Representation (politics); Artificial intelligence; Set (abstract data type); Strengths and weaknesses; Simple (philosophy); Key (lock); Artificial neural network; Feature learning; Machine learning","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":[0.000522711,0.000224929,0.0003864034,0.00009769399,0.0001512565,0.00005925732,0.0006308009,0.00005453277,0.000008249152],"category_scores_gemma":[0.00009829664,0.0001325069,0.0001132085,0.0001723518,0.0001406671,0.0004295114,0.0003965565,0.0001181445,0.00001319185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007828774,"about_ca_system_score_gemma":0.00006089575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002497356,"about_ca_topic_score_gemma":0.000006314018,"domain_scores_codex":[0.9977903,0.0002549258,0.0006700302,0.0003490713,0.000583498,0.0003521264],"domain_scores_gemma":[0.9981955,0.0001361202,0.0008156036,0.0005317581,0.0002241899,0.00009679316],"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":[0.00002873874,0.00004502024,0.03742846,0.00008640031,0.0003013826,0.000005115685,0.001289596,0.9482355,0.007769123,0.0011858,0.00007662026,0.003548306],"study_design_scores_gemma":[0.00189214,0.0001803956,0.01216922,0.0006079295,0.00003565308,0.000005253548,0.0001152476,0.9818466,0.0007525636,0.000006083937,0.002207422,0.0001814743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05036366,0.0001757146,0.9479423,0.00003966939,0.0005319819,0.0006639892,0.000005972487,0.00002941503,0.0002472771],"genre_scores_gemma":[0.9947135,0.00009203773,0.001628949,0.00004644096,0.00001993433,0.00001173028,0.0000010307,0.00001693143,0.003469455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9463134,"threshold_uncertainty_score":0.5403474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04777979186199204,"score_gpt":0.2658761195988801,"score_spread":0.218096327736888,"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."}}