{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006044736,0.0001003769,0.0001668167,0.00009099879,0.00004720179,0.00001433348,0.00002994081,0.00002072821,0.000001439949],"category_scores_gemma":[0.00000141402,0.0001015134,0.000009510882,0.00009753992,0.000008021102,0.00002342057,0.00001150002,0.00009367602,6.164977e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001472625,"about_ca_system_score_gemma":0.000006830368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002911727,"about_ca_topic_score_gemma":2.326344e-7,"domain_scores_codex":[0.9995557,0.000003650445,0.0001590943,0.00009646934,0.0001011561,0.00008392726],"domain_scores_gemma":[0.9998147,0.00008192327,0.00001796863,0.00004292897,0.00001869959,0.00002371352],"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":[0.000008396955,0.00001467239,0.0003295979,0.00009383324,0.00004489971,2.636395e-7,0.0003315388,0.9938949,0.0003160649,0.002624512,0.000004842024,0.002336416],"study_design_scores_gemma":[0.0008309016,0.00009055912,0.01041361,0.0000497312,0.000009639993,3.219018e-7,0.000254893,0.9879583,0.0001974576,0.00001355978,0.00009567187,0.00008536962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.888077,0.00009329557,0.1095589,0.0000046244,0.00005504807,0.0002224603,5.442433e-7,0.00007697621,0.001911141],"genre_scores_gemma":[0.9994253,0.000002724674,0.000476975,0.0000105626,0.00001443503,0.00004302323,0.000003756611,0.000006762852,0.00001646001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1113483,"threshold_uncertainty_score":0.4139596,"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."}}