{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002247024,0.0007647944,0.001214138,0.0008379454,0.0005748913,0.0009870332,0.001751208,0.001131422,0.004056892],"category_scores_gemma":[0.009607419,0.0006551463,0.0007917506,0.0009730844,0.001573883,0.0014162,0.001733464,0.001697254,0.0006390032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001694972,"about_ca_system_score_gemma":0.002172812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004654962,"about_ca_topic_score_gemma":0.005778416,"domain_scores_codex":[0.9987871,0.0004479472,0.00006146169,0.0001847849,0.0004068967,0.0001119486],"domain_scores_gemma":[0.9952019,0.003583647,0.0002913493,0.0004423134,0.0003149933,0.0001656947],"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":[0.00005324485,0.00002594907,0.0003442141,0.00003443314,0.00002287987,0.00003674223,0.00003376209,0.9303408,0.0003633029,0.04155627,0.0007531219,0.02643529],"study_design_scores_gemma":[0.000004480021,0.000005724883,0.00001692791,0.000002696037,0.000001636244,0.000005225736,0.00000117068,0.9912503,0.0001214372,0.008362213,0.0002266848,0.000001528501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006118774,0.0001025662,0.9901484,0.0001781429,0.00002435783,0.00004897122,0.0000405707,0.0003595975,0.002978505],"genre_scores_gemma":[0.4669686,0.000174063,0.528085,0.000208067,0.00006347482,0.0003665587,0.0002068084,0.0001639627,0.003763559],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004654962,"threshold_uncertainty_score":0.01357168,"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."}}