{"id":"W3035954878","doi":"10.48550/arxiv.2006.13169","title":"Experience Replay with Likelihood-free Importance Weights","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Estimator; Temporal difference learning; Suite; Key (lock); Baseline (sea); Bellman equation; Function (biology); Sample (material); Artificial intelligence; Prioritization; Machine learning; Mathematical optimization; Statistics; Mathematics","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0001546439,0.0004868865,0.0004439806,0.000174113,0.0002186072,0.0002576262,0.005408953,0.0002617931,0.00005238559],"category_scores_gemma":[0.00008886932,0.0004915537,0.0001712498,0.0008505267,0.0001970269,0.000672549,0.004433481,0.0009617372,0.0001352441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002327665,"about_ca_system_score_gemma":0.0003616917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000620624,"about_ca_topic_score_gemma":0.00002337434,"domain_scores_codex":[0.9968989,0.00009650527,0.0003177091,0.001828719,0.0002804905,0.000577715],"domain_scores_gemma":[0.9952148,0.00009392775,0.000542443,0.003599651,0.0001904551,0.0003587172],"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":[0.00004930642,0.00003499731,0.02051755,0.00008598699,0.0001072535,0.001537348,0.001393391,0.8445747,0.00002273171,0.1305659,0.001031869,0.00007892094],"study_design_scores_gemma":[0.0007823926,0.0002294336,0.002312491,0.0001895253,0.00006095189,0.0000184098,0.0001347793,0.9744287,0.000285517,0.01779676,0.002771536,0.0009894669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06584028,0.0000387658,0.9241699,0.0003420003,0.000467422,0.0003529632,0.000004253921,0.0006034378,0.008180994],"genre_scores_gemma":[0.9762301,0.0001021066,0.02131359,0.0003621774,0.0001020577,0.000002532066,0.00001375835,0.0000342057,0.001839419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9103898,"threshold_uncertainty_score":0.9999723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05575956341198271,"score_gpt":0.1853098619665042,"score_spread":0.1295502985545215,"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."}}