{"id":"W2890185089","doi":"","title":"Monte-Carlo Tree Search for Constrained POMDPs","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Monte Carlo tree search; Computer science; Partially observable Markov decision process; Mathematical optimization; Monte Carlo method; Markov decision process; Tree (set theory); Action selection; Scale (ratio); Markov process; Machine learning; Markov model; Mathematics; Markov chain","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004897292,0.0001619134,0.0001810694,0.0001975465,0.0004108005,0.001376753,0.0006856057,0.0000895092,0.000002336415],"category_scores_gemma":[0.00007424262,0.0001428641,0.00005322006,0.0003883516,0.00008486136,0.004376268,0.00009978944,0.0001299944,0.0001033088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007809958,"about_ca_system_score_gemma":0.0001623729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000169326,"about_ca_topic_score_gemma":6.462033e-7,"domain_scores_codex":[0.9983284,0.00004247398,0.0005998756,0.0001714437,0.0004737123,0.0003840177],"domain_scores_gemma":[0.9984265,0.00007489701,0.0003131954,0.0003279735,0.000760577,0.00009687597],"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":[0.00007014401,0.0000611916,0.0008270518,0.002419506,0.0000811324,0.000003001856,0.02870303,0.7276844,0.0008026172,0.04022656,0.01211771,0.1870036],"study_design_scores_gemma":[0.0004854695,0.0002639454,0.00007702909,0.00007260291,0.000004670851,0.00003100526,0.0003121753,0.9863509,0.0005168515,0.00000808995,0.01171072,0.0001665401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006091552,0.00003462229,0.9828913,0.0004080106,0.001021461,0.0006697832,0.000002865228,0.0006285235,0.008251899],"genre_scores_gemma":[0.987573,0.000001075806,0.01134834,0.0002760456,0.0002314483,0.00005572253,0.00000711044,0.000009099813,0.0004981319],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9814815,"threshold_uncertainty_score":0.9996599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03579990415296933,"score_gpt":0.284999641127341,"score_spread":0.2491997369743717,"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."}}