{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009233368,0.001093689,0.000875295,0.0005244983,0.0004804293,0.0009793241,0.00132713,0.0009800531,0.003382658],"category_scores_gemma":[0.003173603,0.0006842313,0.0006568441,0.0005514401,0.001172696,0.001330942,0.001258645,0.002362831,0.0005330571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00194274,"about_ca_system_score_gemma":0.002778492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01613567,"about_ca_topic_score_gemma":0.01734652,"domain_scores_codex":[0.9995822,0.0001152426,0.00003045958,0.00009093932,0.0001260588,0.00005501286],"domain_scores_gemma":[0.9987963,0.0007499278,0.0001107295,0.0001265113,0.0001528669,0.00006354065],"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":[0.00002558434,0.00001276635,0.0001263491,0.00004324097,0.00000884306,0.00001760461,0.00001987735,0.9709523,0.0004988022,0.01221856,0.0005739562,0.01550225],"study_design_scores_gemma":[0.000003392486,0.000003878241,0.00001335549,0.000003464468,0.00000115757,0.000002202085,0.000002516304,0.9932376,0.0002264763,0.006217104,0.0002872819,0.000001455431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006973132,0.000245046,0.989495,0.0002470781,0.00003254052,0.00003320701,0.000109297,0.001192264,0.001672422],"genre_scores_gemma":[0.5378485,0.0006367612,0.4564843,0.0002469989,0.00005418414,0.0003374499,0.0005880097,0.0004046705,0.003399159],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01613567,"threshold_uncertainty_score":0.03208351,"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."}}