{"id":"W3103966376","doi":"","title":"Value-driven Hindsight Modelling","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hindsight bias; Leverage (statistics); Computer science; Reinforcement learning; Machine learning; Artificial intelligence; Bellman equation; Exploit; Function (biology); Representation (politics); Mathematical optimization; 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":[0.002746161,0.001259297,0.001524993,0.0006877886,0.0005083992,0.002382816,0.002744855,0.002209631,0.008960513],"category_scores_gemma":[0.0138415,0.0006468284,0.0009899465,0.0008424637,0.002634464,0.00302332,0.002253928,0.003461173,0.001398989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001793863,"about_ca_system_score_gemma":0.001509986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005008611,"about_ca_topic_score_gemma":0.005762549,"domain_scores_codex":[0.9984223,0.000640297,0.00006751217,0.0003792705,0.0002878365,0.0002028689],"domain_scores_gemma":[0.9941795,0.003802243,0.0007083311,0.0004777356,0.0005206157,0.0003115066],"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":[0.00009755873,0.00004621781,0.0009543266,0.0001001855,0.00004701239,0.0001639564,0.0001717616,0.6772872,0.0007521595,0.2944474,0.002944109,0.02298805],"study_design_scores_gemma":[0.00001471047,0.00002085017,0.00008989436,0.00001235276,0.000005425834,0.00002312215,0.00001077939,0.8439957,0.0001605577,0.1546672,0.0009887003,0.00001081561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01530394,0.0003452064,0.9719771,0.001292206,0.00008908684,0.00007158369,0.0003271994,0.0003763613,0.01021728],"genre_scores_gemma":[0.8442179,0.0005997323,0.1295207,0.0005748778,0.0001779496,0.0003221676,0.0004742178,0.0002412814,0.0238713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008960513,"threshold_uncertainty_score":0.02997589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03967133682234385,"score_gpt":0.2352821196128032,"score_spread":0.1956107827904593,"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."}}