{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00105968,0.0002880017,0.0005079266,0.0001216856,0.0001772324,0.00006772976,0.001649984,0.00007967429,0.0005519686],"category_scores_gemma":[0.0005103743,0.000160129,0.0003060506,0.0004488016,0.0007820728,0.0006594834,0.000781845,0.0002034351,0.00010089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001111791,"about_ca_system_score_gemma":0.000358289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003825068,"about_ca_topic_score_gemma":0.0001287552,"domain_scores_codex":[0.9963696,0.0003008253,0.001372936,0.0004974013,0.0008754749,0.0005837789],"domain_scores_gemma":[0.9966134,0.0005785078,0.001062142,0.001095984,0.0005397067,0.0001102188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001188487,0.0001174612,0.0269867,0.00007577734,0.0002214635,0.000003952791,0.004226089,0.3909723,0.1515271,0.0220418,0.00009701517,0.4036115],"study_design_scores_gemma":[0.0002265402,0.000257775,0.0006441232,0.0004261853,0.00003528567,0.000003314034,0.0001262085,0.7462312,0.2482894,0.001731344,0.001817092,0.0002115287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08820091,0.0001469306,0.9072145,0.001083167,0.0007023141,0.0004418059,0.000003650981,0.0000286764,0.00217811],"genre_scores_gemma":[0.9889997,0.00008330243,0.002547973,0.0001527773,0.00004477565,0.000004012653,1.070967e-7,0.00001624279,0.008151135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9046665,"threshold_uncertainty_score":0.6529872,"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."}}