{"id":"W3152801112","doi":"10.48550/arxiv.2104.08543","title":"Planning with Expectation Models for Control","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Reinforcement learning; Variance (accounting); Computer science; Bellman equation; Function (biology); Feature (linguistics); Artificial intelligence; Sample (material); Action (physics); Stochastic modelling; Control (management); Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001338003,0.0002331614,0.0002745148,0.0001570642,0.0001469488,0.0002330499,0.0009564363,0.0001679271,0.000004713927],"category_scores_gemma":[0.00002426631,0.0002572865,0.0001249426,0.0002557884,0.00004184601,0.0005853472,0.000446187,0.0003234261,0.000004005882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462193,"about_ca_system_score_gemma":0.0002311936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001943281,"about_ca_topic_score_gemma":0.000003271111,"domain_scores_codex":[0.9986008,0.00006719126,0.0001530622,0.0007839938,0.0001045634,0.000290429],"domain_scores_gemma":[0.9984336,0.0001678179,0.0002690321,0.0007695253,0.0002698531,0.00009021063],"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":[0.00003494075,0.00001337348,0.0005709289,0.00005154636,0.00009632091,0.00009649772,0.000685914,0.9581109,0.000007354248,0.04025178,0.0000370826,0.00004339852],"study_design_scores_gemma":[0.0009345424,0.00009110289,0.0001377814,0.000138432,0.00006325228,0.000002811176,0.00026841,0.9955419,0.00003926046,0.002438042,0.00003567556,0.0003087325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01944124,0.00003195386,0.978292,0.00004664736,0.0002651429,0.0004265588,0.000002746679,0.0002046288,0.001289078],"genre_scores_gemma":[0.973547,0.00001054072,0.02540855,0.00008503882,0.00004364624,0.000003835052,0.00003056959,0.00001834124,0.0008525208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9541057,"threshold_uncertainty_score":0.999988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0911888882141892,"score_gpt":0.1957893315222335,"score_spread":0.1046004433080443,"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."}}