{"id":"W3037179286","doi":"10.65109/rtpw2660","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Generalization; Scalability; Artificial neural network; 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":[0.004137988,0.001645807,0.001348238,0.0004167529,0.0005727106,0.0009118906,0.001768329,0.001358973,0.0017926],"category_scores_gemma":[0.01920945,0.000670913,0.0006669034,0.0003135226,0.002007719,0.002054756,0.002004788,0.003505345,0.0004145374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001452215,"about_ca_system_score_gemma":0.001330008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004998839,"about_ca_topic_score_gemma":0.003300629,"domain_scores_codex":[0.9982462,0.000504062,0.0001353438,0.0004528239,0.0004155017,0.0002461113],"domain_scores_gemma":[0.9927664,0.004366507,0.0007095444,0.001338063,0.000597645,0.0002218492],"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":[0.0002187982,0.0002114398,0.002198526,0.000117177,0.0001009439,0.00009527949,0.0001142754,0.8874491,0.008168798,0.007319042,0.0009903159,0.0930163],"study_design_scores_gemma":[0.00001983367,0.0001271254,0.0002687812,0.00001085869,0.00001122649,0.00001908912,0.000006847211,0.9924917,0.001903314,0.004889579,0.0002441178,0.000007546327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1361522,0.0007741126,0.8556374,0.0006259442,0.0001102022,0.0001178679,0.00005347353,0.002418019,0.004110711],"genre_scores_gemma":[0.9340534,0.0001630718,0.06412128,0.000275107,0.00004542506,0.0001254652,0.00005802473,0.0001329849,0.001025337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004998839,"threshold_uncertainty_score":0.02188408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01277579907890778,"score_gpt":0.2148214111520931,"score_spread":0.2020456120731853,"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."}}