{"id":"W2950048158","doi":"10.48550/arxiv.1404.3328","title":"Myopic Bounds for Optimal Policy of POMDPs: An extension of Lovejoy's structural results","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Extension (predicate logic); Bounded function; Markov decision process; Mathematical optimization; Relaxation (psychology); Mathematical economics; Upper and lower bounds; Mathematics; Computer science; Markov process; Economics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006952879,0.0015267,0.001980463,0.001733086,0.001114149,0.002557133,0.002782021,0.001802603,0.007739232],"category_scores_gemma":[0.0417317,0.001690645,0.001888814,0.001326481,0.003621367,0.008055786,0.004731831,0.006125759,0.0007201696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002591047,"about_ca_system_score_gemma":0.003247869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001673991,"about_ca_topic_score_gemma":0.001668883,"domain_scores_codex":[0.9949524,0.001622312,0.0002702586,0.0008685989,0.001806421,0.0004799707],"domain_scores_gemma":[0.964982,0.02749284,0.002310343,0.002305309,0.002046606,0.0008629151],"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":[0.000116977,0.00009281409,0.0005116059,0.0002986145,0.00004642801,0.0000941264,0.0003746765,0.2817233,0.001778851,0.6936887,0.001838882,0.01943521],"study_design_scores_gemma":[0.0000339371,0.00007581506,0.0002288039,0.0001091157,0.00001542668,0.00004420773,0.00005361179,0.4987884,0.001122882,0.4972048,0.002297024,0.00002596545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.012051,0.0004864878,0.9753932,0.001051424,0.00004973788,0.00007154021,0.0001937637,0.0001777217,0.01052511],"genre_scores_gemma":[0.75547,0.00170212,0.2348366,0.0007443964,0.0003312766,0.0008673024,0.0005175463,0.0004071475,0.005123606],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007739232,"threshold_uncertainty_score":0.03677082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07299322227582464,"score_gpt":0.2316462662448447,"score_spread":0.15865304396902,"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."}}