{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001716661,0.00009827107,0.0000882036,0.0002520285,0.0001575142,0.0003093906,0.0004271819,0.0000523148,0.00002460476],"category_scores_gemma":[0.00005355211,0.00008536167,0.0000724237,0.0002884244,0.0000301321,0.0006752312,0.00008729096,0.00007443849,0.00007205927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009485179,"about_ca_system_score_gemma":0.0001882145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003941153,"about_ca_topic_score_gemma":0.000004682036,"domain_scores_codex":[0.9989907,0.00003063023,0.0002374607,0.0001278948,0.0002962662,0.000317078],"domain_scores_gemma":[0.9993084,0.0001403856,0.00006059483,0.000319374,0.0001278143,0.00004340975],"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":[0.000008660631,0.00001237244,0.0005312082,0.00002396784,0.000004336427,1.209709e-7,0.000060183,0.7637646,0.0002576734,0.22864,0.003173789,0.003523063],"study_design_scores_gemma":[0.0005281519,0.0001084211,0.003685522,0.000005625651,0.000002218579,7.148709e-7,0.000005177479,0.9848185,0.004562768,0.000252749,0.005919189,0.000111021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003304023,0.000003012163,0.9865721,0.001164288,0.000134925,0.0002759144,0.000001786675,0.000225602,0.008318326],"genre_scores_gemma":[0.9489229,8.143867e-7,0.04930655,0.0003206617,0.0001707168,0.00002568747,0.00004778737,0.000005410782,0.001199501],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9456189,"threshold_uncertainty_score":0.3480948,"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."}}