{"id":"W2786478526","doi":"","title":"Adversarial Policy Gradient for Alternating Markov Games","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Artificial neural network; Computer science; Markov decision process; Markov chain; Gradient descent; Mathematical optimization; Temporal difference learning; Artificial intelligence; Markov process; Machine learning; Mathematics; Statistics","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":[0.0003048087,0.0001733175,0.0001392882,0.0004093356,0.0004046644,0.0005135774,0.001172314,0.00005880692,0.0002070365],"category_scores_gemma":[0.001739506,0.0001808347,0.0001120708,0.0002839671,0.0001294544,0.0005105786,0.0002638427,0.0002624299,0.000197394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001551978,"about_ca_system_score_gemma":0.0001988369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001370964,"about_ca_topic_score_gemma":0.000009269274,"domain_scores_codex":[0.9981179,0.00009509576,0.0003625843,0.0005187051,0.0005746507,0.000331034],"domain_scores_gemma":[0.998107,0.0003809718,0.0002916499,0.0003968338,0.0007213083,0.0001022282],"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":[0.00005587476,0.00005264203,0.003097879,0.000006553353,0.00011782,0.000005023688,0.003055187,0.09530484,0.001172774,0.8742134,0.001622507,0.02129552],"study_design_scores_gemma":[0.0007769259,0.0003773253,0.002612217,0.00005524354,0.000007716234,0.0000101523,0.0002614154,0.9709676,0.0008990321,0.006106345,0.01769534,0.0002306844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006322321,0.000002242926,0.8893006,0.007155095,0.001743713,0.0002850305,0.00000549309,0.0002510566,0.09493446],"genre_scores_gemma":[0.9567552,0.00001355437,0.02975092,0.00036565,0.001178023,0.00008053984,0.00004776444,0.00001830382,0.01179002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9504329,"threshold_uncertainty_score":0.7374223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05030579220343445,"score_gpt":0.3677090667664834,"score_spread":0.317403274563049,"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."}}