{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001828367,0.00120504,0.001253356,0.0005399686,0.0003984932,0.0008780608,0.001063143,0.001212926,0.003692609],"category_scores_gemma":[0.007792008,0.000496726,0.000555927,0.0003530013,0.001671767,0.001162728,0.001379933,0.001903667,0.0004538065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0016767,"about_ca_system_score_gemma":0.00154991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004118285,"about_ca_topic_score_gemma":0.003329647,"domain_scores_codex":[0.9991131,0.000464157,0.00003379303,0.0001444243,0.0001523318,0.00009210389],"domain_scores_gemma":[0.9965191,0.002739364,0.0002177434,0.000127071,0.0002333358,0.0001633551],"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":[0.00006494252,0.00003125739,0.0002983768,0.00004999825,0.0000195218,0.00004271531,0.00004191282,0.9352189,0.0004969276,0.05240951,0.0007614577,0.01056438],"study_design_scores_gemma":[0.000005016308,0.000008715378,0.00001898787,0.000003119792,0.000001553768,0.000003681557,0.000002162266,0.9887982,0.0000904999,0.01089428,0.0001714936,0.000002252687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02031145,0.0002300542,0.9742187,0.0003856224,0.00006183327,0.00006990109,0.00005318905,0.0003344929,0.004334744],"genre_scores_gemma":[0.8357289,0.0003065134,0.1534143,0.00035602,0.00007336227,0.0004107601,0.0001769059,0.000179639,0.009353611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004118285,"threshold_uncertainty_score":0.01235294,"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."}}