{"id":"W3080779222","doi":"10.48550/arxiv.2008.11329","title":"Inverse Policy Evaluation for Value-based Sequential Decision-making","year":2020,"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 Alberta","funders":"","keywords":"Value (mathematics); Inverse; Computer science; Operations research; Mathematics; Machine learning","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":[0.006490166,0.001301521,0.00197149,0.000969825,0.0007352536,0.002051529,0.001551277,0.001775949,0.00347357],"category_scores_gemma":[0.01912988,0.0008511753,0.0008948684,0.0007614467,0.003508955,0.002238491,0.001920443,0.0033242,0.0004683888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003339045,"about_ca_system_score_gemma":0.003693858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005410183,"about_ca_topic_score_gemma":0.004268907,"domain_scores_codex":[0.9962542,0.001929285,0.0001566032,0.0005208014,0.0008886495,0.0002503188],"domain_scores_gemma":[0.9895984,0.008611002,0.0004453151,0.0003102525,0.0007470218,0.0002880094],"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":[0.000103723,0.00006631768,0.0004331543,0.0001013521,0.00004049993,0.00004811394,0.0001321171,0.8829985,0.0004753442,0.08355796,0.0004541354,0.03158889],"study_design_scores_gemma":[0.0000121601,0.00002321638,0.00002482179,0.00001298496,0.000003878784,0.000005341253,0.000004851936,0.9602379,0.0002490336,0.03916143,0.0002594388,0.000005093555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008842974,0.0001974631,0.9871645,0.0002429966,0.00002817639,0.00008921094,0.00002130538,0.0001701631,0.003243267],"genre_scores_gemma":[0.6648573,0.0002780444,0.3304103,0.0002306591,0.00005790273,0.0004953032,0.0001043656,0.0001365486,0.003429437],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006490166,"threshold_uncertainty_score":0.03432369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1482290289717731,"score_gpt":0.2711285996184502,"score_spread":0.122899570646677,"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."}}