{"id":"W4412185637","doi":"10.54254/2755-2721/2025.ast24879","title":"Comparative Study of Reinforcement Learning Performance Based on PPO and DQN Algorithms","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Elevator Systems and Control","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Algorithm; Machine learning; Psychology; Social psychology","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":[0.003908594,0.0009211427,0.0009975961,0.0009796951,0.0004242765,0.0008323222,0.0008476513,0.001029419,0.001296454],"category_scores_gemma":[0.01672993,0.0002274446,0.0003648754,0.0005191324,0.0007513253,0.001121948,0.001051021,0.00115861,0.000251653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009622492,"about_ca_system_score_gemma":0.001423693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006866038,"about_ca_topic_score_gemma":0.003423322,"domain_scores_codex":[0.9986645,0.0004236302,0.0001282556,0.0002717127,0.0003193846,0.0001925655],"domain_scores_gemma":[0.9909142,0.006263346,0.0005988779,0.0004883836,0.001370815,0.0003642697],"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":[0.0006724086,0.000347149,0.005585148,0.0003595017,0.0001165836,0.00006386855,0.0001016885,0.8865452,0.001968978,0.004952437,0.00111074,0.09817628],"study_design_scores_gemma":[0.00004320031,0.0002955003,0.0009649323,0.00001918584,0.00001860687,0.000027402,0.0000337642,0.9957554,0.001303566,0.001174671,0.0003527566,0.00001100317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6184137,0.0043707,0.3554581,0.0009492144,0.0004227158,0.0003698873,0.0002865019,0.001643524,0.01808571],"genre_scores_gemma":[0.9588125,0.0004068264,0.0392713,0.0001032255,0.00002443961,0.000136896,0.0002129284,0.00006323598,0.0009687259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006866038,"threshold_uncertainty_score":0.02067083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00530211984392681,"score_gpt":0.1982041630576057,"score_spread":0.1929020432136789,"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."}}