{"id":"W2902062907","doi":"","title":"Nonlinear Optimization and Symbolic Dynamic Programming for Parameterized Hybrid Markov Decision Processes.","year":2017,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Parameterized complexity; Markov decision process; Computer science; Mathematical optimization; Dynamic programming; Nonlinear system; Markov process; Markov chain; Nonlinear programming; Mathematics; Algorithm; Machine learning","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":[0.00134455,0.000988369,0.001314606,0.0005421769,0.0005372277,0.001291835,0.0009845031,0.00129267,0.005401019],"category_scores_gemma":[0.007868115,0.0006606678,0.0008667693,0.000632936,0.001642889,0.001535238,0.001710922,0.002029825,0.0004076897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002047401,"about_ca_system_score_gemma":0.002158483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01491342,"about_ca_topic_score_gemma":0.01479115,"domain_scores_codex":[0.9994828,0.0002750758,0.00002356709,0.00006779472,0.00007760008,0.00007317973],"domain_scores_gemma":[0.994964,0.004326458,0.0003069671,0.00009223806,0.0001763667,0.0001339452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005082635,0.00002803765,0.0003276803,0.00005667051,0.00004454075,0.00005034754,0.00003935167,0.8913909,0.0001866664,0.1007648,0.0009010046,0.006159245],"study_design_scores_gemma":[0.000005116641,0.000004308438,0.00002810974,0.000004082132,0.00000314011,0.000002332215,0.000004715028,0.9673666,0.00002836089,0.03241411,0.0001363645,0.000002621572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02852984,0.001541579,0.9539257,0.00128749,0.00009917554,0.00005272219,0.0002424064,0.0001870819,0.01413395],"genre_scores_gemma":[0.9059964,0.0008380202,0.08082195,0.000176263,0.00007503984,0.0002538831,0.0003307593,0.0001100215,0.01139759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01491342,"threshold_uncertainty_score":0.02965319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08557820677108352,"score_gpt":0.3627951243467675,"score_spread":0.277216917575684,"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."}}