{"id":"W2956872166","doi":"10.48550/arxiv.1907.04651","title":"Incrementally Learning Functions of the Return","year":2019,"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 Alberta","funders":"","keywords":"Reinforcement learning; Taylor series; Value (mathematics); Computer science; Temporal difference learning; Mathematics; Mathematical optimization; Applied mathematics; Artificial intelligence; Machine learning; Mathematical analysis","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":[0.001447533,0.0006199465,0.0007897884,0.0006093177,0.0001873885,0.0009421733,0.001270529,0.0009755024,0.002038545],"category_scores_gemma":[0.01253875,0.0004176089,0.0004805816,0.0004312893,0.0008556413,0.001811443,0.0009419982,0.00157459,0.0004780183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002866,"about_ca_system_score_gemma":0.0009584964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001905183,"about_ca_topic_score_gemma":0.002065407,"domain_scores_codex":[0.9995319,0.0001349653,0.00002747514,0.0001237356,0.0001316757,0.00005029716],"domain_scores_gemma":[0.9963238,0.002526694,0.0003074165,0.0002757496,0.0004514531,0.0001148784],"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":[0.0002361832,0.0001272603,0.002044699,0.0001078418,0.00005200205,0.00008047876,0.00009478927,0.7700981,0.009733146,0.04372067,0.001780925,0.1719239],"study_design_scores_gemma":[0.000005798071,0.00001826989,0.0001040963,0.000004610589,0.000004023253,0.00001165679,0.000002576132,0.9918416,0.0009423494,0.006872322,0.0001878848,0.000004845718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01900029,0.0001070859,0.9796779,0.0001283725,0.00002467045,0.00002213648,0.00003322161,0.0002843708,0.0007220343],"genre_scores_gemma":[0.7705696,0.0002370288,0.2254807,0.0001284868,0.00005246094,0.0001684488,0.0001356489,0.0001242924,0.003103375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002038545,"threshold_uncertainty_score":0.007655382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05402498703515711,"score_gpt":0.1752706064785677,"score_spread":0.1212456194434106,"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."}}