{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002025758,0.0001068703,0.0001004913,0.0001114037,0.0001835884,0.00005720959,0.0001989646,0.00005277196,0.000005460985],"category_scores_gemma":[0.00002028863,0.0001096309,0.00002114767,0.0003752896,0.00004268524,0.001274338,0.0001301308,0.0001328786,0.00002558579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005572888,"about_ca_system_score_gemma":0.00001931882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008326833,"about_ca_topic_score_gemma":5.329262e-7,"domain_scores_codex":[0.9992925,0.00004635317,0.00008598977,0.0002470389,0.00007362192,0.0002544982],"domain_scores_gemma":[0.9994273,0.00005992224,0.0001020354,0.0002580224,0.00004992411,0.0001027593],"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":[0.00004319753,0.00001975267,0.04204223,0.00002822346,0.00003088632,0.00001235672,0.0007536652,0.8852861,0.0001239684,0.07096841,0.00001561814,0.0006755872],"study_design_scores_gemma":[0.0005733097,0.00008765526,0.01010059,0.00003392547,0.00002437418,0.000007861775,0.0001628294,0.9881592,0.00006875463,0.0001210743,0.0004977189,0.0001627511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1747361,0.00002108137,0.8230492,0.0000172856,0.00009858234,0.00009571839,1.182121e-7,0.0001461194,0.001835802],"genre_scores_gemma":[0.9878357,0.000007089324,0.01149435,0.00005276211,0.00005849269,2.996432e-7,0.000003155426,0.000007728426,0.0005404237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8130996,"threshold_uncertainty_score":0.4470619,"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."}}