{"id":"W2134461419","doi":"","title":"Multi-Step Dyna Planning for Policy Evaluation and Control","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Feature (linguistics); Bellman equation; Function (biology); Mathematical optimization","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":[0.002537735,0.001405849,0.001176405,0.0006925945,0.0008763578,0.00184684,0.001759624,0.001119353,0.00780202],"category_scores_gemma":[0.007086779,0.0007641609,0.0009136051,0.0008137709,0.001232903,0.001722323,0.001667907,0.002584402,0.001027487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002178911,"about_ca_system_score_gemma":0.004062857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01134973,"about_ca_topic_score_gemma":0.01217924,"domain_scores_codex":[0.9984371,0.000612027,0.0001089887,0.000281678,0.0004204887,0.0001396602],"domain_scores_gemma":[0.996204,0.002542666,0.0002487171,0.0003423153,0.000478116,0.0001842376],"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":[0.00006942986,0.00004607566,0.0003304767,0.00008590254,0.00003964983,0.00005575394,0.00006290053,0.9112626,0.0005990005,0.0572073,0.001743479,0.02849745],"study_design_scores_gemma":[0.00001012664,0.00001161796,0.0000257211,0.000006389489,0.000005561772,0.000006239757,0.000004500367,0.9816223,0.0003399436,0.01648874,0.001471973,0.000006847336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003118241,0.0001517507,0.9917389,0.0003335405,0.00008161251,0.00007907916,0.00009979168,0.0008692318,0.003527914],"genre_scores_gemma":[0.4737065,0.0003823212,0.5171502,0.0003012455,0.00008499135,0.0007703005,0.000345761,0.0003469137,0.006911709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01134973,"threshold_uncertainty_score":0.02610034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1780201854582342,"score_gpt":0.4527883759956488,"score_spread":0.2747681905374146,"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."}}