{"id":"W4399732880","doi":"10.2139/ssrn.4857358","title":"Relative Monte Carlo for Reinforcement Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Monte Carlo method; Reinforcement learning; Computer science; Statistical physics; Artificial intelligence; Econometrics; Economics; Mathematics; Physics; Statistics","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":[0.006672742,0.001316145,0.003153314,0.001328683,0.0009759663,0.002242185,0.003450825,0.003315184,0.009902784],"category_scores_gemma":[0.02975829,0.001503579,0.001207297,0.001562414,0.003638153,0.003560605,0.002966986,0.005255021,0.001141835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002698961,"about_ca_system_score_gemma":0.002339807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008252722,"about_ca_topic_score_gemma":0.006132213,"domain_scores_codex":[0.9969203,0.001976877,0.00009153001,0.0003429426,0.0004779014,0.0001904761],"domain_scores_gemma":[0.9788124,0.01865275,0.0005465951,0.000794505,0.0007660855,0.0004277672],"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":[0.00008768115,0.0000452344,0.0001987463,0.00007359212,0.00004671135,0.00002316865,0.00003261898,0.8421471,0.000117962,0.1453821,0.0009028445,0.01094226],"study_design_scores_gemma":[0.00001280615,0.000007598863,0.00001940806,0.000008146328,0.000005001863,0.000003909166,0.000001744546,0.9385678,0.0000432154,0.06110435,0.0002220438,0.000004008737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005109724,0.0005809857,0.9906285,0.0003889692,0.00008041449,0.000036901,0.00005146934,0.0002096748,0.002913168],"genre_scores_gemma":[0.6040685,0.001073545,0.3767154,0.0005888094,0.0003806635,0.0009312477,0.0003954109,0.0005089985,0.0153375],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009902784,"threshold_uncertainty_score":0.03528923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361410814969361,"score_gpt":0.2673314610651457,"score_spread":0.2537173529154521,"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."}}