{"id":"W4380684831","doi":"10.1109/tmlcn.2023.3285543","title":"Reinforcement Learning With Non-Cumulative Objective","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Machine Learning in Communications and Networking","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Markov decision process; Bottleneck; Function (biology); Mathematical optimization; Process (computing); Artificial intelligence; Bellman equation; Convergence (economics); Markov process; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007618597,0.0002513401,0.0002548784,0.0005335822,0.001207693,0.0001975483,0.0007956886,0.00008786351,0.000008254284],"category_scores_gemma":[0.00001180635,0.0002404095,0.00005816173,0.001808919,0.000130842,0.0003740879,0.00005779747,0.001648093,0.0000383013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000116169,"about_ca_system_score_gemma":0.00005497864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001893606,"about_ca_topic_score_gemma":0.0001273481,"domain_scores_codex":[0.9981065,0.0003501801,0.0003837814,0.0004007058,0.0003144858,0.000444297],"domain_scores_gemma":[0.9977914,0.0009765303,0.0002033096,0.0008691465,0.00007346908,0.00008615135],"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":[0.00001975176,0.00002257803,0.002196075,0.000009126217,0.00004137909,0.000004962521,0.002425261,0.951214,0.00003268653,0.0002909965,0.000004778526,0.04373838],"study_design_scores_gemma":[0.00065041,0.0004308019,0.001286329,0.0002140542,0.00001505862,0.00000926853,0.0002431675,0.9929357,0.00004291605,0.00005338526,0.003846241,0.0002726665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002517091,0.0001203763,0.9921656,0.0006609696,0.0001516712,0.0003045242,3.039966e-7,0.0005100913,0.00356936],"genre_scores_gemma":[0.987604,0.00193266,0.008692925,0.00009497306,0.00002495306,0.00009409474,0.00001303601,0.00003370062,0.0015097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9850869,"threshold_uncertainty_score":0.9803615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02896642669377206,"score_gpt":0.2792376464679182,"score_spread":0.2502712197741461,"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."}}