{"id":"W2970634945","doi":"","title":"Maximum Entropy Monte-Carlo Planning","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Softmax function; Computer science; Mathematical optimization; Monte Carlo method; Principle of maximum entropy; Entropy (arrow of time); Convergence (economics); Monte Carlo tree search; Rate of convergence; Mathematics; Algorithm; Artificial intelligence; Artificial neural network; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002830931,0.0001772,0.0001982282,0.0001971961,0.0001752823,0.001551168,0.0007138158,0.00008540272,0.000006665509],"category_scores_gemma":[0.00003936516,0.0001569497,0.00004702847,0.0003686353,0.00001738331,0.006964986,0.0001437961,0.0002247441,0.0006029911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000833642,"about_ca_system_score_gemma":0.000068126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001645132,"about_ca_topic_score_gemma":4.443702e-8,"domain_scores_codex":[0.9982387,0.00004288091,0.0006075,0.0001727888,0.0005893479,0.0003487213],"domain_scores_gemma":[0.9987784,0.00003831192,0.0005012694,0.0003946403,0.0002060077,0.00008138188],"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":[0.000003989242,0.000003057188,0.002709328,0.0002527319,0.000005868183,0.000001395493,0.00198405,0.987396,0.00008236301,0.001813404,0.0008049926,0.0049428],"study_design_scores_gemma":[0.000315035,0.00006491468,0.0004511671,0.0001497373,0.000002711188,0.00003740868,0.0003146356,0.981351,0.00008384191,0.00001410437,0.01702678,0.0001887173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03950355,0.0001985681,0.9446462,0.0002639795,0.002392554,0.0005497491,9.442412e-7,0.0007539804,0.01169045],"genre_scores_gemma":[0.9965496,0.000001476818,0.001976555,0.0003910754,0.00007125986,0.00001803193,0.000007384701,0.000008920176,0.0009757107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.957046,"threshold_uncertainty_score":0.9994853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01568430427876681,"score_gpt":0.2420348712932825,"score_spread":0.2263505670145157,"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."}}