{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002122272,0.001354986,0.001488997,0.0006072269,0.0006770871,0.001311785,0.001603379,0.001437287,0.001911989],"category_scores_gemma":[0.008949227,0.001013582,0.0009527974,0.0008016557,0.002112797,0.002289736,0.002454994,0.002492904,0.0004809549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001861763,"about_ca_system_score_gemma":0.001858583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005495476,"about_ca_topic_score_gemma":0.004884318,"domain_scores_codex":[0.9989925,0.0003989766,0.00006038646,0.0002292833,0.0001822303,0.0001366612],"domain_scores_gemma":[0.9932486,0.005583693,0.0003434941,0.0004521526,0.0001923321,0.0001798489],"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":[0.00005959822,0.00002288885,0.0002743639,0.00004065114,0.00001424474,0.000028085,0.00002488042,0.9812733,0.0003905275,0.007426738,0.0002732452,0.01017147],"study_design_scores_gemma":[0.000008864743,0.000006893461,0.00001964028,0.00000260005,0.000001949219,0.000003016931,0.000004100065,0.9891785,0.0002203001,0.01047866,0.00007405551,0.000001403709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.026054,0.0001724942,0.9710621,0.0003146198,0.00001661563,0.00005459333,0.0000767501,0.000881153,0.001367621],"genre_scores_gemma":[0.7129428,0.0002545043,0.2835015,0.0001914455,0.00004307366,0.000352909,0.0003378025,0.0002464361,0.002129526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005495476,"threshold_uncertainty_score":0.01350814,"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."}}