{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001502311,0.0001613952,0.0001779936,0.00009589578,0.0002435668,0.00137973,0.0007470396,0.00007362029,0.00000227342],"category_scores_gemma":[0.00004172248,0.0001450934,0.00004597916,0.000470494,0.00002054869,0.006555713,0.0001399896,0.0002248868,0.0002334532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004749471,"about_ca_system_score_gemma":0.00007753161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000101712,"about_ca_topic_score_gemma":2.319524e-8,"domain_scores_codex":[0.9983612,0.00004620646,0.0006012482,0.0001714859,0.0005517049,0.0002681784],"domain_scores_gemma":[0.9989947,0.00002759341,0.0004096042,0.0002271328,0.0001958845,0.0001450718],"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":[0.000002049996,0.000001674566,0.0000464126,0.000192244,0.000003930943,0.00000104473,0.003502943,0.9871282,0.00003445769,0.005780919,0.0005928027,0.002713316],"study_design_scores_gemma":[0.0001908515,0.00004973335,0.000006788403,0.00005670924,0.000003813395,0.00001255082,0.000117895,0.9856862,0.0001119211,0.00001346693,0.0135807,0.0001693163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007209667,0.00007403104,0.9920077,0.001341783,0.0004454891,0.0002241824,6.629239e-7,0.0006161762,0.00456905],"genre_scores_gemma":[0.9845763,0.000003455125,0.01354416,0.001610212,0.0001380287,0.00001407061,0.00001235864,0.00000903102,0.00009235185],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9838554,"threshold_uncertainty_score":0.9996569,"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."}}