{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001011179,0.0009839527,0.0008579387,0.0002950404,0.0003411005,0.0009490675,0.001594134,0.0008724889,0.003084588],"category_scores_gemma":[0.002531181,0.0003408674,0.0004868247,0.0001886713,0.001053778,0.0009246762,0.001338967,0.00143883,0.0003572588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008763081,"about_ca_system_score_gemma":0.0009967914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007398173,"about_ca_topic_score_gemma":0.00714985,"domain_scores_codex":[0.9995986,0.0001051463,0.00002607116,0.00008634796,0.0001132641,0.00007049707],"domain_scores_gemma":[0.9990103,0.0005635775,0.00009765029,0.0001094855,0.0001426315,0.00007621785],"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":[0.0001124057,0.00007172674,0.0004920569,0.0001027267,0.00004070289,0.00003639329,0.0000465412,0.9276539,0.001407924,0.01376504,0.0007427736,0.05552786],"study_design_scores_gemma":[0.000008784979,0.0000272353,0.00003756945,0.000004520301,0.000002742655,0.000003028125,0.000002231188,0.9974535,0.0002005523,0.002057937,0.0001994381,0.000002355564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0728725,0.0009609102,0.9098207,0.0004107554,0.0001075524,0.0001139233,0.00007527644,0.0007395375,0.01489879],"genre_scores_gemma":[0.9447827,0.0002412195,0.0521008,0.000103781,0.00003078856,0.00009298831,0.00007215355,0.00004738665,0.00252828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007398173,"threshold_uncertainty_score":0.01471025,"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."}}