{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001850111,0.0009487451,0.0009754075,0.0004051682,0.0003377169,0.0009116239,0.00186991,0.001020626,0.00257806],"category_scores_gemma":[0.008772,0.0005447011,0.0004121794,0.0003538256,0.001066185,0.001756032,0.00189182,0.002285409,0.0004711982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007850429,"about_ca_system_score_gemma":0.001322819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003197896,"about_ca_topic_score_gemma":0.003901338,"domain_scores_codex":[0.9993297,0.0001988158,0.00004298083,0.0001642628,0.0001785569,0.00008568219],"domain_scores_gemma":[0.9973793,0.001325912,0.0003182789,0.0003704713,0.0004002744,0.0002057193],"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":[0.000546072,0.0002337599,0.002287847,0.0001551727,0.00007806326,0.0001500703,0.0001629152,0.8239309,0.006564411,0.01575601,0.001844781,0.14829],"study_design_scores_gemma":[0.0000229621,0.00005798732,0.0001364824,0.000006262977,0.000006330436,0.00001571849,0.000006982532,0.9943181,0.001240617,0.003925484,0.0002574705,0.000005670574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0563372,0.0002202611,0.9404783,0.0002617552,0.00008032285,0.00008095252,0.00004318414,0.0008223216,0.001675775],"genre_scores_gemma":[0.8809198,0.00007971282,0.1158179,0.0001169113,0.00003291276,0.0001229749,0.00008033373,0.00008594806,0.002743572],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003197896,"threshold_uncertainty_score":0.00978446,"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."}}