{"id":"W4210266050","doi":"10.1109/cinti53070.2021.9668479","title":"Deep Reinforcement Learning with DQN vs. PPO in VizDoom","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Convergence (economics); Reinforcement; Quality (philosophy); Track (disk drive); Object (grammar); Machine learning; Human–computer interaction; Engineering","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":[0.0002589552,0.0001667678,0.0001909958,0.0001182672,0.0001056424,0.0002511451,0.000533391,0.00005733693,0.0002933374],"category_scores_gemma":[0.00008965797,0.0001434451,0.00004034431,0.0007083161,0.00003024454,0.0004781985,0.0004033702,0.000346095,0.000189262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001019998,"about_ca_system_score_gemma":0.0001455599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003950444,"about_ca_topic_score_gemma":0.00005153931,"domain_scores_codex":[0.9982871,0.00007924813,0.0003099949,0.0004042871,0.0004844974,0.0004349133],"domain_scores_gemma":[0.9990413,0.00009215873,0.00009644184,0.0005601531,0.0001137402,0.00009624647],"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":[0.000006291817,0.0000123755,0.007102697,0.00001158719,0.00001272963,0.0001147374,0.0005368548,0.9662264,0.00007711438,0.02417328,0.00009300607,0.001632939],"study_design_scores_gemma":[0.0006154284,0.0002068217,0.002166497,0.00004379592,0.000003693451,0.00002970639,0.0001660436,0.987105,0.001559853,0.00005795791,0.007807495,0.0002377123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001536357,0.00003221213,0.9361022,0.0007064392,0.0001199868,0.000103888,7.40249e-9,0.0001791133,0.06121984],"genre_scores_gemma":[0.8957915,0.0000337193,0.08339889,0.0009336182,0.0000302744,0.00001301429,0.000006854319,0.00001603834,0.01977613],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8942551,"threshold_uncertainty_score":0.5849521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01072931158088935,"score_gpt":0.2251434012773191,"score_spread":0.2144140896964297,"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."}}