{"id":"W3211776917","doi":"","title":"Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Interpretation (philosophy); Representation (politics); Tree (set theory); Object (grammar); Machine learning; Programming language; 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":[0.00068902,0.0006339587,0.000987099,0.0005709145,0.0002532614,0.0009020405,0.001148058,0.001415432,0.003342853],"category_scores_gemma":[0.003271149,0.0004216012,0.0006465372,0.0005993787,0.0006852605,0.001854768,0.001054285,0.00200567,0.0006155787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008532925,"about_ca_system_score_gemma":0.0006928886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002955977,"about_ca_topic_score_gemma":0.003631151,"domain_scores_codex":[0.9997844,0.00006199536,0.00001309914,0.00006180545,0.00005043279,0.00002829824],"domain_scores_gemma":[0.9991818,0.0004271361,0.00007385484,0.0001141202,0.0001551349,0.00004795562],"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":[0.0002164225,0.00008690282,0.000835606,0.0001434177,0.00006029879,0.0001142902,0.0001004932,0.6851385,0.007658031,0.07430694,0.004598367,0.2267407],"study_design_scores_gemma":[0.000004955828,0.00001083237,0.00003296142,0.000005820677,0.000003075143,0.000004780659,0.000002983944,0.9729772,0.00040301,0.02630807,0.000243712,0.000002677934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01181855,0.0001731966,0.9861356,0.0001641201,0.00005264311,0.00002191572,0.0001087144,0.0006586711,0.0008665062],"genre_scores_gemma":[0.689185,0.0003352169,0.3058345,0.0002119392,0.00006441436,0.0001590811,0.0006378865,0.0003354582,0.003236381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003342853,"threshold_uncertainty_score":0.01118302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02155870844513758,"score_gpt":0.2752711759624968,"score_spread":0.2537124675173592,"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."}}