{"id":"W3040979139","doi":"10.48550/arxiv.2007.06184","title":"Efficient Planning in Large MDPs with Weak Linear Function Approximation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov decision process; Bellman equation; Oracle; Mathematical optimization; Computer science; Computation; Function (biology); Set (abstract data type); Time horizon; State (computer science); Core (optical fiber); Approximation algorithm; Expected value; Markov process; Algorithm; Mathematics","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":[0.000272104,0.0002696356,0.0002671098,0.0003153578,0.0001173505,0.0001050494,0.0009059134,0.0002035445,0.0000107257],"category_scores_gemma":[0.00003570544,0.0002928396,0.00007796055,0.0008397048,0.0000381397,0.0001809477,0.001159786,0.0008251055,0.00008684491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002392892,"about_ca_system_score_gemma":0.0001489152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002240531,"about_ca_topic_score_gemma":0.000005107099,"domain_scores_codex":[0.9982517,0.0001117388,0.0002185051,0.0008950611,0.0001725318,0.0003504063],"domain_scores_gemma":[0.9987444,0.00006013768,0.0003010687,0.000689603,0.00009375125,0.0001110117],"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":[0.00005353596,0.00003849088,0.005474017,0.00007778331,0.00003030209,0.0001007548,0.000490893,0.9543699,0.000009928704,0.03928792,0.00002954959,0.00003693064],"study_design_scores_gemma":[0.0006847418,0.0001224247,0.003568589,0.0001805085,0.00003012662,0.000001709021,0.0001507033,0.9941328,0.00001868033,0.0005212853,0.0002711321,0.0003173149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0803251,0.00001344993,0.9158729,0.00008080854,0.0003015685,0.0003364988,0.000001808887,0.0002729424,0.002794892],"genre_scores_gemma":[0.9931456,0.000006140441,0.006246763,0.00007708328,0.00005673492,0.000001275566,0.00003359764,0.00001830259,0.0004145285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9128205,"threshold_uncertainty_score":0.9999524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06112267459238138,"score_gpt":0.1937169603688299,"score_spread":0.1325942857764486,"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."}}