{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006122738,0.001492026,0.002643846,0.0009702576,0.001022745,0.002292452,0.00238522,0.001614931,0.003704455],"category_scores_gemma":[0.02266287,0.0009144124,0.002019787,0.001933316,0.00462113,0.005587672,0.003579093,0.003424331,0.0004175862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003602321,"about_ca_system_score_gemma":0.004039453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01302247,"about_ca_topic_score_gemma":0.008047289,"domain_scores_codex":[0.995828,0.001739962,0.0002372782,0.0008137505,0.0007040473,0.0006768627],"domain_scores_gemma":[0.9742094,0.02278475,0.0008034616,0.001226675,0.000533734,0.0004420262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002300351,0.0000604942,0.0002729636,0.0001040129,0.00002684887,0.00006585027,0.0001303614,0.9353813,0.0007823022,0.05091004,0.0004275563,0.01160827],"study_design_scores_gemma":[0.00003494243,0.00005060704,0.00004873492,0.00001151036,0.000008657588,0.00001110425,0.00001966038,0.9496373,0.0004347416,0.04951318,0.0002209847,0.000008573035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03647405,0.0004263147,0.9587808,0.0006565696,0.00002676656,0.0001275602,0.0001949287,0.0007266018,0.002586423],"genre_scores_gemma":[0.6532414,0.000774727,0.3422932,0.0002910444,0.00008082038,0.0004474717,0.00056511,0.0002928948,0.00201325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01302247,"threshold_uncertainty_score":0.03238052,"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."}}