{"id":"W4403564633","doi":"10.48550/arxiv.2410.09368","title":"Towards a Domain-Specific Modelling Environment for Reinforcement Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Reinforcement; Domain (mathematical analysis); Computer science; Cognitive science; Psychology; Artificial intelligence; Social psychology; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007844283,0.001406323,0.001038525,0.001006829,0.0007065036,0.004161165,0.004151185,0.002922102,0.006914085],"category_scores_gemma":[0.01849486,0.001689411,0.002648983,0.0007758429,0.002141132,0.004291475,0.004044732,0.006837924,0.002859052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001291009,"about_ca_system_score_gemma":0.002747271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002213069,"about_ca_topic_score_gemma":0.002437491,"domain_scores_codex":[0.9954278,0.002088614,0.0005417481,0.0005714683,0.001133595,0.000236716],"domain_scores_gemma":[0.9901856,0.006340491,0.0005313084,0.001437247,0.001206738,0.0002985923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002380703,0.0003909143,0.001456644,0.0009936069,0.0001247301,0.0005984415,0.001542652,0.4664852,0.01361362,0.3659239,0.009389493,0.1392427],"study_design_scores_gemma":[0.00007666796,0.00007039286,0.00008009593,0.0001900423,0.00002817316,0.0001698773,0.00007355892,0.8626311,0.009650981,0.06964519,0.05733247,0.00005151849],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009345096,0.00003473723,0.9950386,0.0001963247,0.00002570438,0.00006860885,0.00006215897,0.00286584,0.0007734799],"genre_scores_gemma":[0.03298924,0.0001846517,0.9627765,0.0002271602,0.00003072714,0.0004195466,0.0003998246,0.001368803,0.00160349],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007844283,"threshold_uncertainty_score":0.04148501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1393643901273245,"score_gpt":0.2123780578668136,"score_spread":0.07301366773948906,"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."}}