{"id":"W4283800411","doi":"10.1609/aaai.v36i9.21220","title":"Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Research Foundation Singapore; National Research Foundation","keywords":"Computer science; Mathematical optimization; Variance (accounting); Maximization; Iterative learning control; Upper and lower bounds; Parametric statistics; Sample (material); Markov decision process; Optimization problem; Artificial intelligence; Algorithm; Mathematics; Control (management)","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":[0.0006465044,0.0001637506,0.0002735991,0.0002202735,0.0002829623,0.000122728,0.001081897,0.00003823738,0.00003623553],"category_scores_gemma":[0.000685041,0.0001378115,0.00009288763,0.0007006733,0.0001512166,0.0001651497,0.0003826451,0.0003063689,0.00000107316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007593295,"about_ca_system_score_gemma":0.00007522106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001571131,"about_ca_topic_score_gemma":0.000002860163,"domain_scores_codex":[0.9984174,0.00003856053,0.0004909126,0.0003765727,0.0003992551,0.0002773449],"domain_scores_gemma":[0.9985045,0.0003201553,0.0005209874,0.0001707541,0.000444729,0.00003883881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001784024,0.0003004521,0.0004829993,0.00003272331,0.00001416983,4.605608e-7,0.01561549,0.3678657,0.003850417,0.5959662,0.00001958798,0.01567343],"study_design_scores_gemma":[0.00005489782,0.0004614329,0.0001270122,0.000100783,0.000005430808,0.000002474783,0.002578873,0.9373246,0.03806037,0.02109521,0.00004279706,0.0001461089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1878004,0.00002838944,0.8076231,0.001327134,0.0004354257,0.0006272051,0.00002376853,0.00004596138,0.002088637],"genre_scores_gemma":[0.9866087,0.000002277894,0.0131086,0.00009695049,0.00003324847,0.00008266862,0.000001885937,0.000009925995,0.00005575145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7988083,"threshold_uncertainty_score":0.5619788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04515529792387129,"score_gpt":0.3091709383972863,"score_spread":0.264015640473415,"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."}}