{"id":"W3037467471","doi":"","title":"Optimization Methods for Interpretable Differentiable Decision Trees Applied to Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Differentiable function; Artificial intelligence; Computer science; Decision tree; Machine learning; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005333195,0.0002777409,0.0003048142,0.0002107343,0.0002828102,0.0008001918,0.0009480398,0.00008848518,0.000355646],"category_scores_gemma":[0.00166922,0.0002769208,0.00005617124,0.0003408766,0.00007679058,0.0003610577,0.0003320014,0.0002214307,0.0001444947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007642848,"about_ca_system_score_gemma":0.00008293344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002852261,"about_ca_topic_score_gemma":0.00002941455,"domain_scores_codex":[0.9976686,0.00009265255,0.0007137721,0.0007300209,0.000400184,0.0003947581],"domain_scores_gemma":[0.9976984,0.0009778774,0.0001908091,0.0002588972,0.0005732987,0.0003006918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001894194,0.0000307662,0.000003480498,0.000006897231,0.00001729041,0.000001447624,0.0009758162,0.2389711,0.002429908,0.505233,0.0001845996,0.2519562],"study_design_scores_gemma":[0.00004207273,0.0005356396,0.000004470387,0.00004262568,0.000009797623,0.000001349291,0.0006850243,0.8677044,0.02463484,0.1041531,0.001916012,0.0002706771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001309084,0.00001059357,0.9926955,0.002476905,0.0004605241,0.0005602703,0.00002237621,0.0001246187,0.00351834],"genre_scores_gemma":[0.4270589,0.00006312189,0.5714808,0.001014411,0.00008501841,0.0000863987,0.00003436273,0.00001539456,0.0001616447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6287332,"threshold_uncertainty_score":0.9999683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.119486721409573,"score_gpt":0.3891250946442423,"score_spread":0.2696383732346694,"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."}}