{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003165225,0.000993378,0.00162888,0.0008877086,0.0004642179,0.001357166,0.001481454,0.001944374,0.003655325],"category_scores_gemma":[0.01087652,0.000858883,0.001003867,0.0008018921,0.001171273,0.001280624,0.001663615,0.003037168,0.0004806542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001496233,"about_ca_system_score_gemma":0.001690874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00653463,"about_ca_topic_score_gemma":0.005546076,"domain_scores_codex":[0.999061,0.0005474807,0.00006129478,0.0001077518,0.0001590392,0.00006335475],"domain_scores_gemma":[0.9950851,0.004109002,0.0001852974,0.0001254515,0.0004006736,0.00009442944],"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":[0.00003175816,0.00003649028,0.0001943122,0.00006399811,0.00002822209,0.00003202224,0.00006927187,0.9185212,0.0003473948,0.04437378,0.0005327627,0.03576877],"study_design_scores_gemma":[0.000003921501,0.000004412381,0.00001143064,0.000004594219,0.000001748174,0.000001431925,0.000001787061,0.9922602,0.00003072524,0.00757459,0.0001039187,0.000001355303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002825992,0.0002052287,0.9960168,0.0001121619,0.00002311156,0.00002498965,0.0000146343,0.00008467009,0.0006924346],"genre_scores_gemma":[0.3687263,0.0005487055,0.625159,0.0001637648,0.0001136688,0.0004660086,0.0001692509,0.0003251865,0.004328085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00653463,"threshold_uncertainty_score":0.01673955,"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."}}