{"id":"W1758031947","doi":"10.48550/arxiv.1206.3285","title":"Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Function (biology); Limit (mathematics); Mathematical optimization; Function approximation; State (computer science); Linear approximation; Linear programming; Artificial intelligence; Algorithm; Mathematics; Nonlinear system; Artificial neural network","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":[0.001275479,0.0008478198,0.0009517409,0.0004985373,0.0004573659,0.0009585,0.001277655,0.001093393,0.003294965],"category_scores_gemma":[0.003862632,0.0006270082,0.0005747338,0.0006258675,0.001383964,0.001503889,0.001411386,0.00141293,0.0003768268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073436,"about_ca_system_score_gemma":0.001509038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007459655,"about_ca_topic_score_gemma":0.006504701,"domain_scores_codex":[0.9993908,0.0002407641,0.00003178,0.0001282652,0.0001223654,0.00008589787],"domain_scores_gemma":[0.9983981,0.001109318,0.0001248587,0.000166153,0.0001111701,0.00009038184],"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":[0.00006698437,0.00003064029,0.0003396661,0.00003768453,0.00002131559,0.00004654857,0.00005983285,0.9609173,0.0006179055,0.01725781,0.000253055,0.0203512],"study_design_scores_gemma":[0.000008228252,0.00001646994,0.00002427571,0.000002626411,0.000002723134,0.000005666138,0.000004262212,0.9918371,0.0002131493,0.007690482,0.0001921632,0.00000278215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03115027,0.0001692802,0.9649688,0.0002230426,0.00002496319,0.00004052421,0.00005501866,0.000677253,0.002690889],"genre_scores_gemma":[0.7979031,0.0001407247,0.1978676,0.0001108836,0.00002568199,0.0001491866,0.00009955,0.00009618563,0.003607178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007459655,"threshold_uncertainty_score":0.01483244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0529436338934253,"score_gpt":0.1830294782193934,"score_spread":0.1300858443259681,"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."}}