{"id":"W4408119902","doi":"10.5220/0013123800003896","title":"Towards a Domain-Specific Modelling Environment for Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Domain (mathematical analysis); Artificial intelligence; Human–computer interaction; Mathematics","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":[0.0004414308,0.0001228893,0.0001421342,0.00009611346,0.000119891,0.00005405051,0.0004465748,0.00004332136,0.000007828245],"category_scores_gemma":[0.00002428134,0.0001137982,0.00006483516,0.0001291864,0.00002017651,0.0001710613,0.0002552881,0.0001101751,0.000008968463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001177317,"about_ca_system_score_gemma":0.00002214341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002026946,"about_ca_topic_score_gemma":5.489953e-8,"domain_scores_codex":[0.9990656,0.00003037026,0.0001920947,0.0003166447,0.0001310607,0.0002642275],"domain_scores_gemma":[0.9992001,0.0003498547,0.00003508814,0.0003622146,0.0000199868,0.00003272802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003007667,0.000003399522,0.000001462279,0.000008755779,0.000006827338,5.601993e-7,0.0001134408,0.682541,0.00016083,0.2905922,0.00007306117,0.02649543],"study_design_scores_gemma":[0.0003173458,0.00006656371,0.00001076719,0.00002025433,0.00000245047,9.936435e-7,0.00006044124,0.385933,0.004819936,0.0958121,0.5127647,0.0001914211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001083944,0.000273402,0.9967127,0.0003274275,0.0002754919,0.0002339706,1.052409e-7,0.0004705328,0.001597905],"genre_scores_gemma":[0.006596883,0.000132205,0.9906291,0.00008998805,0.00002090918,0.0000889189,0.000001258452,0.000007189864,0.002433587],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5126916,"threshold_uncertainty_score":0.4640554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04706039575070385,"score_gpt":0.2766106961904504,"score_spread":0.2295503004397465,"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."}}