{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00543351,0.001236092,0.001109033,0.0005308621,0.0005100612,0.001294697,0.002205249,0.001752661,0.001716086],"category_scores_gemma":[0.02422237,0.0005308024,0.0005913692,0.0004913739,0.002574202,0.004265449,0.002996078,0.003233082,0.0003593082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001544604,"about_ca_system_score_gemma":0.001227307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00182994,"about_ca_topic_score_gemma":0.00134238,"domain_scores_codex":[0.9969656,0.001385818,0.0001570431,0.0006322673,0.0006181087,0.0002412579],"domain_scores_gemma":[0.9928296,0.004283119,0.0007503356,0.001149494,0.0006547752,0.0003327299],"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":[0.0004312453,0.000262067,0.002188361,0.0001218722,0.0000775058,0.0001338497,0.000201384,0.8005844,0.005004506,0.1033005,0.00158243,0.08611185],"study_design_scores_gemma":[0.00002428655,0.0001568242,0.000315456,0.00001347419,0.0000079824,0.00004127024,0.00001128427,0.9676082,0.001464374,0.02995051,0.0003950158,0.00001135376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02904793,0.0001884272,0.9682295,0.0003602101,0.00003614953,0.00005525281,0.00003456314,0.0003038667,0.001744114],"genre_scores_gemma":[0.840907,0.0002200414,0.1549858,0.0003245996,0.00006744876,0.0002516364,0.0001003724,0.0001455325,0.002997478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00543351,"threshold_uncertainty_score":0.02873552,"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."}}