{"id":"W2970667219","doi":"","title":"A Geometric Perspective on Optimal Representations for Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Insect and Pesticide Research","field":"Agricultural and Biological Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Representation (politics); Bellman equation; Perspective (graphical); Value (mathematics); Class (philosophy); Relaxation (psychology); Domain (mathematical analysis); Function (biology); Adversarial system; Artificial intelligence; Space (punctuation); Mathematical optimization; Machine learning; Mathematics; Mathematical analysis","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":[0.002718878,0.00136026,0.001213262,0.001079729,0.000539965,0.002438909,0.002075523,0.002105938,0.00611102],"category_scores_gemma":[0.009884493,0.0006350218,0.001285677,0.001011801,0.004102342,0.006184517,0.002779073,0.004632681,0.0007374539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001828698,"about_ca_system_score_gemma":0.0009781967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009167027,"about_ca_topic_score_gemma":0.0006796424,"domain_scores_codex":[0.9984774,0.0007827472,0.00006613429,0.0002629283,0.0003000594,0.000110658],"domain_scores_gemma":[0.9961592,0.002520352,0.0003584345,0.0004922997,0.0003041112,0.0001655718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002031545,0.00002474137,0.0001594662,0.00005885779,0.00002066097,0.00002972262,0.00006309716,0.1650715,0.0005957137,0.8204253,0.000786314,0.01274432],"study_design_scores_gemma":[0.0000110711,0.00005888654,0.00005158821,0.00002212966,0.000005720637,0.00002204666,0.00001649543,0.3599539,0.0003161518,0.6377535,0.001776929,0.00001162743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002936944,0.0002423548,0.9928888,0.0007133491,0.0000399571,0.0000163144,0.00004263304,0.00004565931,0.003073987],"genre_scores_gemma":[0.5372477,0.001636784,0.4529467,0.000673082,0.0005618193,0.0003472781,0.0002471107,0.0002417362,0.006097752],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00611102,"threshold_uncertainty_score":0.02044344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0356229744796313,"score_gpt":0.3060931110972628,"score_spread":0.2704701366176315,"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."}}