{"id":"W2949221912","doi":"10.48550/arxiv.1807.05887","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Artificial neural network; Tree (set theory); Function (biology); Machine learning; Feature (linguistics); Decision tree; Deep neural networks; 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":[0.001749548,0.0008931967,0.00103937,0.0005603288,0.0003396481,0.001094326,0.001536992,0.00124299,0.002154851],"category_scores_gemma":[0.008679004,0.0006211749,0.0006206784,0.0004818058,0.001057389,0.001658103,0.00143441,0.002510761,0.000472952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001498696,"about_ca_system_score_gemma":0.001256039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005193389,"about_ca_topic_score_gemma":0.006591105,"domain_scores_codex":[0.9993883,0.000282709,0.00002755732,0.0001131822,0.0001237833,0.00006441259],"domain_scores_gemma":[0.9974305,0.001820927,0.0002143454,0.0001882414,0.0002464479,0.00009944972],"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":[0.00008405765,0.00005962587,0.001099765,0.00006769628,0.00003773385,0.00007343654,0.000107375,0.8998029,0.0007998296,0.03672406,0.001883772,0.05925968],"study_design_scores_gemma":[0.000003449854,0.000007682151,0.00001577282,0.000003820359,0.000001486038,0.000002823869,0.000002295032,0.9895403,0.00008767533,0.01020692,0.0001264221,0.000001342305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01706348,0.00035204,0.9799566,0.0003543707,0.00003619983,0.0000353532,0.0000667203,0.0006851793,0.001450087],"genre_scores_gemma":[0.7760451,0.0003434333,0.2196323,0.0003850073,0.00007383149,0.0002331009,0.0002543762,0.0001990322,0.002833786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005193389,"threshold_uncertainty_score":0.01087385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06759661223877765,"score_gpt":0.2031394876909434,"score_spread":0.1355428754521658,"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."}}