{"id":"W4392907203","doi":"10.32920/25412866","title":"RLML: A Domain-specific Modelling Language for Reinforcement Learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Reinforcement learning; Syntax; Domain (mathematical analysis); Abstraction; Artificial intelligence; Domain-specific language; Simplicity; Constraint (computer-aided design); Modeling language; Machine learning; Programming language; Software engineering; Human–computer interaction; Software; Engineering","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":[0.004133691,0.001724766,0.0009552184,0.001021104,0.0007038953,0.003594622,0.004231346,0.002970116,0.01470644],"category_scores_gemma":[0.01094101,0.001723643,0.002505885,0.0007696002,0.001755198,0.003199234,0.002524828,0.005513063,0.006492706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001216847,"about_ca_system_score_gemma":0.003352384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00416104,"about_ca_topic_score_gemma":0.004807334,"domain_scores_codex":[0.9970739,0.001061651,0.0005411874,0.000398296,0.0007461411,0.0001788423],"domain_scores_gemma":[0.9945832,0.003209508,0.0004188481,0.0008049963,0.0008221489,0.0001613464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003775302,0.0002600431,0.001269798,0.002218665,0.0001590139,0.00102961,0.00181778,0.1987278,0.01622469,0.5257913,0.08124296,0.1708808],"study_design_scores_gemma":[0.0001864973,0.0001226095,0.0001740751,0.0004520064,0.00006087884,0.0006098637,0.0001045005,0.4172414,0.01442544,0.1120543,0.4544308,0.0001375939],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0004656957,0.00007369592,0.9832053,0.0002701483,0.00007400454,0.0001374901,0.0008834924,0.01319549,0.001694719],"genre_scores_gemma":[0.0297454,0.0004358226,0.9527943,0.0005885435,0.00009180863,0.00123758,0.003589139,0.006115187,0.005402206],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01470644,"threshold_uncertainty_score":0.04919791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0357708060542106,"score_gpt":0.2899136415220822,"score_spread":0.2541428354678715,"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."}}