{"id":"W2604173138","doi":"10.1609/aaai.v31i1.11056","title":"Hindsight Optimization for Hybrid State and Action MDPs","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Computer science; Mathematical optimization; Markov decision process; Upper and lower bounds; Piecewise linear function; Formalism (music); Action selection; Scaling; Markov process; Mathematics","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":[0.0004135352,0.0001722267,0.0001872616,0.00007091468,0.0006507449,0.0008486864,0.001567603,0.00005386104,0.00001496342],"category_scores_gemma":[0.0003829001,0.0001333292,0.00006579987,0.00008539462,0.0002374178,0.0008545278,0.0003061534,0.0001678831,0.00001149336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002358873,"about_ca_system_score_gemma":0.00006773343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003031957,"about_ca_topic_score_gemma":0.000006164641,"domain_scores_codex":[0.9987124,0.000008609003,0.0003362002,0.0004388256,0.0002511015,0.0002529129],"domain_scores_gemma":[0.9983923,0.00005423789,0.000491461,0.0003699696,0.0006120459,0.00007996772],"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":[0.00007742668,0.00007983086,0.0001090985,0.00006302319,0.00001409892,2.305121e-7,0.0005894447,0.001242178,0.0106125,0.7176135,0.0001672417,0.2694314],"study_design_scores_gemma":[0.00002583225,0.000110356,0.00009586079,0.00008991689,0.00000693536,0.000002757192,0.00003396317,0.5655491,0.2440212,0.1899026,0.00003530056,0.0001262213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07966634,0.00001431817,0.912864,0.004058878,0.0004544891,0.0003777137,0.000007569011,0.00005476828,0.002501922],"genre_scores_gemma":[0.9805498,0.0001090674,0.01884595,0.000102927,0.00005024127,0.00003131237,4.195479e-7,0.000009406275,0.0003008706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9008834,"threshold_uncertainty_score":0.8183903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1316459554872544,"score_gpt":0.330156495202359,"score_spread":0.1985105397151047,"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."}}