{"id":"W3041568888","doi":"10.48550/arxiv.2007.06049","title":"An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Equivalence (formal languages); Reinforcement learning; Function (biology); Mathematics; Computer science; Algorithm; Applied mathematics; Statistics; Discrete mathematics; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002586107,0.0003115852,0.0003498718,0.0002785933,0.0002084863,0.000246375,0.001964125,0.000239014,0.00001270957],"category_scores_gemma":[0.00006916998,0.0003866324,0.000077873,0.0007534458,0.0001811265,0.0009569177,0.002471619,0.0008577104,0.0000364907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001963361,"about_ca_system_score_gemma":0.0001582039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001664704,"about_ca_topic_score_gemma":0.00001343382,"domain_scores_codex":[0.99771,0.00008151682,0.0002984805,0.001346827,0.0001437835,0.0004193533],"domain_scores_gemma":[0.997907,0.0001496369,0.0002603363,0.001319003,0.00008625261,0.0002777162],"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":[0.00000835211,0.00001393736,0.0952823,0.00005426534,0.00001707439,0.0001353939,0.001441585,0.8971105,0.0000408716,0.005652719,0.000005871861,0.0002371333],"study_design_scores_gemma":[0.0002989263,0.0001201877,0.02176746,0.0001413206,0.00002451639,0.000004854392,0.000393633,0.974341,0.00005338312,0.002280532,0.0001037164,0.0004704291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3299673,0.000006645383,0.6686628,0.00005647303,0.000197019,0.000179885,0.000004286217,0.0001430314,0.0007826277],"genre_scores_gemma":[0.9906296,0.00008242221,0.008809366,0.00005880731,0.00007641125,0.000001529623,0.00001939098,0.00001673193,0.0003057176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6606624,"threshold_uncertainty_score":0.9998586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.130837707818112,"score_gpt":0.2445806165634153,"score_spread":0.1137429087453033,"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."}}