{"id":"W4391021135","doi":"10.1109/cdc49753.2023.10383590","title":"Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Bounding overwatch; Norm (philosophy); Function (biology); Computer science; Algorithm; Discrete mathematics; Combinatorics; Mathematics; Artificial intelligence; Philosophy","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":[0.01192784,0.004070438,0.00387819,0.002178155,0.001326682,0.003782691,0.003631003,0.00346557,0.004944775],"category_scores_gemma":[0.05231923,0.001459299,0.002332182,0.001962627,0.003745122,0.006791804,0.005045742,0.006509022,0.0009042412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005310389,"about_ca_system_score_gemma":0.004668274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01072762,"about_ca_topic_score_gemma":0.00717291,"domain_scores_codex":[0.993182,0.00298835,0.0003250818,0.00106849,0.001651813,0.00078418],"domain_scores_gemma":[0.9498321,0.04238505,0.002138725,0.001839224,0.002477929,0.00132697],"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":[0.00018944,0.00006365732,0.0003850581,0.0001926311,0.00007546118,0.00005277861,0.00005418398,0.9512744,0.0002186169,0.03673149,0.0008855446,0.009876733],"study_design_scores_gemma":[0.000009725315,0.00003158728,0.00003742896,0.00002649935,0.000009359089,0.000007304062,0.000008920052,0.9736486,0.0001330746,0.02585181,0.000229075,0.00000661388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01470758,0.001524715,0.9750762,0.001495455,0.0001316803,0.0001086031,0.0003013815,0.0004299518,0.006224326],"genre_scores_gemma":[0.6695445,0.003004621,0.3142244,0.0009908468,0.0003620663,0.001070146,0.001682066,0.0006150917,0.008506186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01192784,"threshold_uncertainty_score":0.0630812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02607248693463956,"score_gpt":0.2568377678037991,"score_spread":0.2307652808691595,"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."}}