{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000570996,0.0001907419,0.0001928742,0.0001587946,0.0007244019,0.001519798,0.001011354,0.00007473079,0.00002002722],"category_scores_gemma":[0.003311063,0.0001870748,0.00004509869,0.0001367336,0.0001657665,0.000724161,0.000197886,0.0001597444,0.00002771581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007012043,"about_ca_system_score_gemma":0.0003116529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006661389,"about_ca_topic_score_gemma":0.000009924099,"domain_scores_codex":[0.9981322,0.000030503,0.0004228441,0.0005265074,0.0006049556,0.0002829976],"domain_scores_gemma":[0.9975454,0.0004579496,0.0003649498,0.0004239057,0.001112457,0.00009532688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000102481,0.00009447585,0.00004507399,0.00005637786,0.00001825066,0.000002994846,0.0001418467,0.3627232,0.0002147511,0.1072295,0.00001683178,0.5293542],"study_design_scores_gemma":[0.00007573079,0.0001768983,0.00008543318,0.00009293173,0.000005369565,0.00000491836,0.00001799006,0.9757916,0.002661178,0.02066498,0.0002150462,0.0002078811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003148207,0.00001316371,0.9944566,0.0008966205,0.0003028356,0.0005759243,0.000009169749,0.0000913414,0.0005061686],"genre_scores_gemma":[0.6324118,0.00005590521,0.367228,0.000091006,0.00004212803,0.00006534733,0.00001998289,0.00001006372,0.00007580429],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6292635,"threshold_uncertainty_score":0.9995167,"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."}}