{"id":"W2912943342","doi":"","title":"Improving generalization in reinforcement learning on Atari 2600 games","year":2019,"lang":"en","type":"article","venue":"International journal of advance research, ideas and innovations in technology","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Hyperparameter; Machine learning; Regularization (linguistics); Overfitting; Deep learning; Transfer of learning; Artificial neural network","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":[0.001845066,0.0009495034,0.0009189586,0.0003229072,0.0003871973,0.0005941556,0.001271712,0.0007998252,0.00210978],"category_scores_gemma":[0.007616494,0.0003402559,0.0005445998,0.0001716334,0.0009679478,0.001168163,0.001361564,0.002072161,0.000375787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001202893,"about_ca_system_score_gemma":0.0009031365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01069953,"about_ca_topic_score_gemma":0.009996091,"domain_scores_codex":[0.9994803,0.0002208323,0.00002480809,0.0001050069,0.00008168199,0.00008741313],"domain_scores_gemma":[0.9980896,0.00120653,0.0001199898,0.0001810671,0.0002525782,0.0001502941],"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":[0.0001440566,0.0002007713,0.001672173,0.00005167436,0.00003496259,0.00007295355,0.00009733612,0.9633986,0.001419371,0.004940718,0.001100155,0.02686722],"study_design_scores_gemma":[0.00001073549,0.00005409471,0.0001533148,0.000004251443,0.000002434342,0.000004066214,0.000008229817,0.9972152,0.0002829755,0.002105478,0.0001563108,0.000002848823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6366027,0.0004519364,0.3485243,0.001011201,0.0001666256,0.0002314599,0.0001823757,0.001440518,0.01138885],"genre_scores_gemma":[0.9597404,0.00007868638,0.03666147,0.0002140858,0.00001788165,0.00009698206,0.0001615655,0.00006113211,0.002967791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01069953,"threshold_uncertainty_score":0.02127451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01771163940650869,"score_gpt":0.3392445821240863,"score_spread":0.3215329427175776,"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."}}