{"id":"W2997123841","doi":"10.1609/aaai.v34i04.5885","title":"Monte-Carlo Tree Search in Continuous Action Spaces with Value Gradients","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center; National Research Foundation","keywords":"Monte Carlo tree search; Discretization; Smoothness; Action (physics); Tree (set theory); Mathematical optimization; Computer science; Monte Carlo method; Set (abstract data type); Space (punctuation); Mathematics; Discrete space; Exploit; Algorithm; Mathematical analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000538283,0.0003592117,0.0004558781,0.0002110817,0.0001837481,0.000450014,0.002832656,0.0001315191,0.00003612246],"category_scores_gemma":[0.0004840193,0.0002636396,0.0001283965,0.00164722,0.0004841139,0.0008977421,0.0004815933,0.0006313548,0.0001348214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009675231,"about_ca_system_score_gemma":0.0001563139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003632215,"about_ca_topic_score_gemma":0.0001644631,"domain_scores_codex":[0.9967723,0.00005482976,0.0007389112,0.0008744354,0.0009426572,0.0006168689],"domain_scores_gemma":[0.9982061,0.0001540546,0.000389405,0.0003747543,0.0006651433,0.0002105762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005889928,0.0004493342,0.008594979,0.0001099255,0.00005331714,0.00001067773,0.01743008,0.004253126,0.0501667,0.7345434,0.0001924607,0.1836071],"study_design_scores_gemma":[0.00005619053,0.0009146956,0.001148165,0.000333282,0.0000169531,0.000007894726,0.004727217,0.2886295,0.6813947,0.02222917,0.0001080701,0.0004341491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9621522,0.00003773089,0.01565155,0.0148611,0.0003642404,0.0008920852,0.000004313952,0.0001900994,0.005846688],"genre_scores_gemma":[0.9963641,0.00004003906,0.002945227,0.0003744133,0.00009335823,0.00003761027,1.86934e-7,0.00002359218,0.000121497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7123142,"threshold_uncertainty_score":0.9999816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1234016045069758,"score_gpt":0.3139371520565129,"score_spread":0.1905355475495371,"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."}}