{"id":"W2905224739","doi":"10.1609/aaai.v33i01.33014504","title":"A Comparative Analysis of Expected and Distributional Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Convergence (economics); Computer science; Mathematical optimization; Linear approximation; Mathematics; Econometrics; Artificial intelligence; Nonlinear system; Economics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003359134,0.0001613113,0.0004066781,0.0002322665,0.0001067681,0.0001128815,0.0009235543,0.00005440448,0.0001170206],"category_scores_gemma":[0.0001931425,0.0001248806,0.0001229727,0.001321612,0.0002087877,0.0002783328,0.0003987144,0.0002454377,0.00002345416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004101829,"about_ca_system_score_gemma":0.00005639227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002537192,"about_ca_topic_score_gemma":0.000001524624,"domain_scores_codex":[0.9983263,0.00002029066,0.0005444512,0.000334095,0.0005556439,0.0002192445],"domain_scores_gemma":[0.9983392,0.0001428087,0.0006018691,0.0002148651,0.0006465844,0.00005467383],"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":[0.00003833142,0.00003322822,0.005183639,0.00002521669,0.0001819694,6.440613e-8,0.002483032,0.1878407,0.01686059,0.7865614,0.000009007363,0.0007828295],"study_design_scores_gemma":[0.00003060654,0.0002628663,0.003514804,0.0000872216,0.00007305278,5.882295e-7,0.0008840607,0.8796436,0.1128692,0.00246625,0.0000274769,0.0001403232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5583579,0.00001454652,0.428612,0.0004564256,0.0001560045,0.0004282589,0.000002577864,0.00005624675,0.01191603],"genre_scores_gemma":[0.9984943,0.00001322775,0.001073685,0.00002723443,0.00000814152,0.000007750928,0.000002779266,0.000003157189,0.0003697247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7840952,"threshold_uncertainty_score":0.5092483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05897849748042289,"score_gpt":0.3011855220912152,"score_spread":0.2422070246107923,"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."}}