{"id":"W4389974594","doi":"10.48550/arxiv.2312.11348","title":"Monte Carlo Tree Search in the Presence of Transition Uncertainty","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Monte Carlo tree search; Computer science; Regret; Context (archaeology); Monte Carlo method; Tree (set theory); Suite; Algorithm; Mathematical optimization; Machine learning; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004365759,0.0002562089,0.000497231,0.0009719733,0.0001383904,0.000112448,0.003611705,0.000276168,0.00008079243],"category_scores_gemma":[0.001203591,0.0001978461,0.0003006994,0.003127796,0.0005365051,0.0003263116,0.001043143,0.001207072,0.0001342837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002162743,"about_ca_system_score_gemma":0.0003423094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002632553,"about_ca_topic_score_gemma":0.002781394,"domain_scores_codex":[0.9953068,0.001267504,0.0005166953,0.001244252,0.001152302,0.000512423],"domain_scores_gemma":[0.9938743,0.003400405,0.0002294011,0.001744867,0.0006359716,0.0001150348],"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":[0.0001450648,0.00007324896,0.001216042,0.00003017171,0.00002271804,0.0003857584,0.002280997,0.9930764,0.00002166383,0.0006927245,0.000423231,0.001631968],"study_design_scores_gemma":[0.0006274084,0.00009370063,0.01498643,0.0001092121,0.00002222694,0.00000282374,0.00867031,0.9056959,0.00008501547,0.06924966,0.000191325,0.0002659581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9260553,0.00006680425,0.07082748,0.0007959372,0.0003176268,0.0009500625,0.000194425,0.00006316396,0.000729186],"genre_scores_gemma":[0.9965836,0.0002208897,0.00009030402,0.00001785827,0.00006116878,0.00000384975,0.000009130224,0.00001908045,0.002994082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08738048,"threshold_uncertainty_score":0.806793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3588932717929086,"score_gpt":0.3327703864944682,"score_spread":0.02612288529844048,"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."}}