{"id":"W2796389682","doi":"10.1109/cdc.2018.8619180","title":"Renewal Monte Carlo: Renewal Theory Based Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Monte Carlo method; Estimator; Computer science; Reinforcement learning; Mathematical optimization; Importance sampling; Variance (accounting); Key (lock); Markov process; Mathematics; Artificial intelligence; Statistics; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002072426,0.0008034789,0.0006877814,0.0004495359,0.0004151678,0.0008907776,0.003810432,0.0006170758,0.0005407925],"category_scores_gemma":[0.0004779,0.0007564789,0.0004258682,0.0003582847,0.0002076,0.0003029463,0.005202097,0.001584738,0.0003861968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004118427,"about_ca_system_score_gemma":0.0007656166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003486342,"about_ca_topic_score_gemma":0.00001770059,"domain_scores_codex":[0.9944819,0.0005650746,0.001049966,0.001495626,0.001400413,0.001007079],"domain_scores_gemma":[0.9951114,0.0003746675,0.0008181372,0.002928717,0.0004465787,0.0003204693],"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":[0.00002968143,0.00001686552,0.0002786995,0.00009283238,0.0001032599,0.0000222967,0.0004737737,0.9771503,0.00003123613,0.01877756,0.00191656,0.001106943],"study_design_scores_gemma":[0.0005437168,0.0003753787,0.00005593165,0.000281233,0.00004787187,0.000005084078,0.00003139045,0.984942,0.001045304,0.003177209,0.008586192,0.0009087511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006479621,0.00006895103,0.882419,0.0004849526,0.002296482,0.0005729146,9.323588e-7,0.001195076,0.1123137],"genre_scores_gemma":[0.780091,0.00005425807,0.1241427,0.001154315,0.0007145887,0.0001111773,0.00006371665,0.0001046963,0.09356356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.779443,"threshold_uncertainty_score":0.9994886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0209271306621518,"score_gpt":0.2568127963650557,"score_spread":0.2358856657029039,"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."}}