{"id":"W3038915804","doi":"10.48550/arxiv.2007.02151","title":"Variational Policy Gradient Method for Reinforcement Learning with General Utilities","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Gradient method; Mathematical optimization; Mathematical economics; Artificial intelligence; Mathematics; Engineering; Structural engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003725591,0.0004109095,0.0004075156,0.0003491293,0.0003312871,0.000241218,0.001531544,0.0002015517,0.00002418396],"category_scores_gemma":[0.0001463259,0.0004392444,0.0002338728,0.0005688369,0.00007848632,0.000341117,0.001669094,0.0006952606,0.00002420274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000501142,"about_ca_system_score_gemma":0.0007563678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002714289,"about_ca_topic_score_gemma":0.000006017784,"domain_scores_codex":[0.9976386,0.0001849609,0.0003106407,0.00110392,0.0002355172,0.0005264016],"domain_scores_gemma":[0.9979854,0.0002502952,0.0004803401,0.0007657353,0.0002893114,0.0002289508],"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":[0.00003553065,0.000008258074,0.0002061186,0.00006777054,0.0001227015,0.00001685696,0.0004377372,0.5731953,0.000005650074,0.4256883,0.0001067519,0.000109],"study_design_scores_gemma":[0.0007231524,0.0003310014,0.0002451683,0.00005477043,0.00007830565,0.000004298919,0.00008274635,0.9799717,0.00004948191,0.01353138,0.004456535,0.0004714672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007936066,0.000009513629,0.993703,0.0006936134,0.0003079615,0.0006290032,0.000005936843,0.0003329565,0.003524388],"genre_scores_gemma":[0.7467031,0.00004147375,0.2407061,0.0004168398,0.000328299,0.00001012463,0.0001217696,0.00003844571,0.01163385],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7529969,"threshold_uncertainty_score":0.9998059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.084019057565281,"score_gpt":0.2294337399251543,"score_spread":0.1454146823598733,"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."}}