{"id":"W3175989421","doi":"","title":"On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Realizability; Markov decision process; Bellman equation; Bounded function; Mathematical optimization; Mathematics; Function (biology); Time horizon; Linear programming; Computer science; Markov process; Algorithm","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":[0.0003066844,0.0000962684,0.000119286,0.00007618061,0.0001110891,0.00001929752,0.0003768023,0.0000453016,0.00001300764],"category_scores_gemma":[0.00006504116,0.00008387577,0.00007523394,0.0008505505,0.00005903051,0.00008457292,0.0002378487,0.0002564231,0.000008451404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008259735,"about_ca_system_score_gemma":0.0001040482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000236188,"about_ca_topic_score_gemma":0.00001574698,"domain_scores_codex":[0.9989112,0.0002769307,0.0001254899,0.000411611,0.00009673391,0.0001780235],"domain_scores_gemma":[0.9991449,0.0001394058,0.0000848262,0.0005177782,0.0000667542,0.00004629732],"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":[0.00002090757,0.0001013645,0.007528195,0.000007394762,0.000007385507,0.00003549762,0.0002176147,0.9044794,0.00006390787,0.08727524,0.00001340449,0.000249708],"study_design_scores_gemma":[0.0003407193,0.00007926116,0.04206268,0.00004048285,0.000005866256,0.000002319782,0.0001156443,0.9520106,0.0005402629,0.004644806,0.00006194968,0.00009537202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6178568,0.000007583748,0.3812328,0.00007810732,0.0001540968,0.0000405111,0.000001256564,0.00003071073,0.000598093],"genre_scores_gemma":[0.9986802,0.00000258251,0.0006609762,0.00009897156,0.00001312106,1.367723e-7,0.000001541489,0.000004609571,0.000537873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3808234,"threshold_uncertainty_score":0.3420354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03489768521518928,"score_gpt":0.1983558477494463,"score_spread":0.163458162534257,"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."}}