{"id":"W2904784373","doi":"10.1609/aaai.v33i01.33017530","title":"Deep Reactive Policies for Planning in Stochastic Nonlinear Domains","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Reinforcement learning; Markov decision process; Mathematical optimization; Stochastic optimization; Artificial intelligence; Probabilistic logic; Stochastic control; Benchmark (surveying); Inference; Optimal control; Mathematics; Markov process","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":[0.0004606169,0.0001867879,0.0002624969,0.0001815494,0.0001113263,0.0001581543,0.001376208,0.00007311651,0.00001404452],"category_scores_gemma":[0.0004417554,0.0001422228,0.00009447114,0.0005062504,0.0001031275,0.0002857118,0.0002465566,0.000337336,0.00004734273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004483835,"about_ca_system_score_gemma":0.00006885958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008095622,"about_ca_topic_score_gemma":0.000008685588,"domain_scores_codex":[0.9985023,0.00001367491,0.0003834377,0.0004271384,0.0003098743,0.0003635322],"domain_scores_gemma":[0.9989045,0.0002360255,0.0002858904,0.000227161,0.0002900074,0.00005645198],"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":[0.000123132,0.0001763531,0.001176084,0.00005604514,0.00001702704,4.605911e-7,0.007776757,0.01278682,0.01690841,0.9208343,0.00002258967,0.04012204],"study_design_scores_gemma":[0.00006105392,0.0002737787,0.000490009,0.000264734,0.000004814098,0.000003309367,0.001056319,0.8806535,0.04134133,0.07559466,0.00005525101,0.0002012456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6051303,0.00002754132,0.3813776,0.00355082,0.0007354973,0.001075121,0.000005601571,0.000125012,0.007972495],"genre_scores_gemma":[0.9895657,0.000002009824,0.00994067,0.0001493789,0.00007898578,0.00003121562,5.307613e-7,0.00001171173,0.000219839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8678667,"threshold_uncertainty_score":0.5799679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04538887102499332,"score_gpt":0.3166275926497552,"score_spread":0.2712387216247618,"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."}}