{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002524281,0.000984428,0.00107177,0.0006305808,0.0005183385,0.002541231,0.003290753,0.001969233,0.005238359],"category_scores_gemma":[0.006751325,0.001191874,0.001962691,0.000577734,0.001096427,0.002930422,0.003801362,0.005059225,0.002714153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007500327,"about_ca_system_score_gemma":0.001519769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002467749,"about_ca_topic_score_gemma":0.004531206,"domain_scores_codex":[0.9984832,0.0006026552,0.0001461113,0.000258463,0.0003884509,0.0001209272],"domain_scores_gemma":[0.9975121,0.001129491,0.0001754408,0.0006101627,0.0003896455,0.0001831492],"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":[0.0003027573,0.000335841,0.001754291,0.000436462,0.0001549918,0.0003710323,0.0006611721,0.6277623,0.0125358,0.203638,0.005742456,0.1463049],"study_design_scores_gemma":[0.00002516637,0.00002941552,0.00006593845,0.00003750694,0.00002208581,0.00005728919,0.00002254454,0.9527412,0.003294975,0.0341096,0.009577196,0.0000171133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001111601,0.00002057196,0.9962263,0.0000689713,0.00001471756,0.00002777443,0.00004343743,0.00183761,0.000648964],"genre_scores_gemma":[0.09109825,0.0001842683,0.9043769,0.0001903373,0.00004266131,0.0002506273,0.0004109649,0.0009829025,0.002463078],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005238359,"threshold_uncertainty_score":0.01752406,"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."}}