{"id":"W2045192098","doi":"10.1109/iat.2006.108","title":"Resolution-Based Policy Search for Imperfect Information Differential Games","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Perfect information; Imperfect; Computer science; Discretization; Differential game; Sequential game; Differential (mechanical device); Mathematical optimization; Zero-sum game; Game theory; Nash equilibrium; Mathematical economics; Mathematics","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":[0.002500339,0.000757799,0.001532524,0.00066448,0.0004072942,0.0008629255,0.001322194,0.00118611,0.001243303],"category_scores_gemma":[0.009940548,0.0005876687,0.0005834592,0.000449741,0.001592119,0.001314127,0.00186003,0.001525513,0.000157219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016287,"about_ca_system_score_gemma":0.0009284826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002039554,"about_ca_topic_score_gemma":0.001214754,"domain_scores_codex":[0.9989929,0.0006146476,0.00004493238,0.0001157278,0.0001430631,0.00008882191],"domain_scores_gemma":[0.994135,0.004709482,0.0005146947,0.0002156731,0.000197699,0.0002275593],"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":[0.00004061546,0.00002660005,0.0002705356,0.00003591374,0.00002217899,0.00004636437,0.00004732191,0.9703403,0.0003356914,0.02125891,0.0001970684,0.007378696],"study_design_scores_gemma":[0.00001069738,0.00001072272,0.00001764044,0.000002724573,0.000001824115,0.000005768784,0.000004558973,0.9944927,0.00008258805,0.005278231,0.00009036832,0.000002216239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03419644,0.0002052375,0.963253,0.0002123908,0.00002718596,0.00005343678,0.00002140753,0.00009604257,0.001934843],"genre_scores_gemma":[0.8583748,0.0001775907,0.1395177,0.0001159178,0.00002672615,0.0001950994,0.00005265094,0.00003378289,0.00150581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002500339,"threshold_uncertainty_score":0.01322323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0111374520453231,"score_gpt":0.2576978047175407,"score_spread":0.2465603526722176,"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."}}