{"id":"W3167763832","doi":"10.21428/594757db.8472938b","title":"General Deep Reinforcement Learning in NES Games","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Acadia University","funders":"","keywords":"Reinforcement learning; Domain (mathematical analysis); Computer science; Video game; Artificial intelligence; Entertainment; Field (mathematics); Deep learning; Domain knowledge; Focus (optics); Hyperparameter; Human–computer interaction; Multimedia","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":[0.0002256893,0.0001234133,0.0001483453,0.0001068707,0.00008360812,0.0002173239,0.0004471202,0.00004997872,0.0002696391],"category_scores_gemma":[0.0001067517,0.0001196518,0.00005309073,0.0004714885,0.00002076562,0.0003863196,0.0004428505,0.0002562273,0.0001047132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007251823,"about_ca_system_score_gemma":0.0001157561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003175975,"about_ca_topic_score_gemma":0.00001894854,"domain_scores_codex":[0.9986317,0.00008356136,0.000299244,0.0003123328,0.0003228559,0.0003503236],"domain_scores_gemma":[0.9993075,0.00006676875,0.00006778513,0.0004132283,0.00007778945,0.0000669065],"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":[5.945127e-7,0.000006800605,0.007720022,0.000006151557,0.000006109567,0.00004643699,0.0003082526,0.9276136,0.0003470455,0.05924447,0.0001437232,0.004556769],"study_design_scores_gemma":[0.0002823832,0.00004233002,0.005346089,0.00001296401,0.000001587453,0.0000129232,0.00007949282,0.9838771,0.001484186,0.0001664873,0.008533145,0.0001613763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004267049,0.0000612618,0.9334214,0.0007320551,0.0002371025,0.00006040801,6.729941e-9,0.0001817727,0.06103889],"genre_scores_gemma":[0.8092791,0.00006459135,0.1400854,0.0009447923,0.00006661564,0.00001052981,0.000006961735,0.00001131182,0.04953062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8050121,"threshold_uncertainty_score":0.487926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01572402921390724,"score_gpt":0.2488639597852059,"score_spread":0.2331399305712987,"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."}}