{"id":"W3157293568","doi":"10.48550/arxiv.2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and\\n Optimization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoregressive model; Computer science; Conditional independence; Covariance; Feed forward; Artificial intelligence; Econometrics; Mathematics; Statistics","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":[0.001621693,0.001337895,0.001507522,0.0006257014,0.0003787195,0.001406784,0.001474976,0.001239336,0.004173945],"category_scores_gemma":[0.007067887,0.0008449552,0.0007010391,0.0006641016,0.0009200646,0.001736247,0.00113462,0.003222947,0.001043171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001652581,"about_ca_system_score_gemma":0.002405619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01487694,"about_ca_topic_score_gemma":0.01483262,"domain_scores_codex":[0.9991768,0.0003376791,0.0000462032,0.0001761225,0.0001803466,0.00008285898],"domain_scores_gemma":[0.9970208,0.002334724,0.0001679011,0.0001805674,0.0002257558,0.00007030628],"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":[0.00004685017,0.00003883012,0.0002488143,0.00005236328,0.00002519854,0.00002719581,0.00002514477,0.9571813,0.0003644383,0.01185501,0.0009505927,0.0291843],"study_design_scores_gemma":[0.000002927748,0.000006039709,0.00002144833,0.000004033982,0.000002149997,0.000002017848,0.000001703305,0.9959238,0.0001180916,0.003718619,0.0001970284,0.000002169068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006408984,0.0004654214,0.9897523,0.0002936818,0.00003919018,0.00003308079,0.0001158235,0.00106464,0.001826933],"genre_scores_gemma":[0.7065876,0.0009643268,0.2818551,0.0003992682,0.0001412592,0.00043983,0.0007999225,0.0005608205,0.008251959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01487694,"threshold_uncertainty_score":0.02958065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08714489944938392,"score_gpt":0.2331941443887187,"score_spread":0.1460492449393348,"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."}}