{"id":"W4382866769","doi":"10.1609/icaps.v33i1.27238","title":"Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach","year":2023,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Secretaría de Ciencia y Técnica, Universidad de Buenos Aires; International Development Research Centre; Agencia Nacional de Investigación e Innovación","keywords":"Reinforcement learning; Heuristics; Computer science; Heuristic; Task (project management); Set (abstract data type); Controller (irrigation); Supervisory control; Domain (mathematical analysis); Artificial intelligence; Space (punctuation); Control (management); Machine learning; Mathematical optimization; Mathematics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001185994,0.0001223167,0.0001335016,0.0001727995,0.0003050532,0.0003131578,0.0007733498,0.0000540721,0.000001440601],"category_scores_gemma":[0.001478542,0.00007995291,0.00005088946,0.0002534189,0.0000498132,0.0003389716,0.0001360489,0.000177734,0.000004620727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003266862,"about_ca_system_score_gemma":0.00002796871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004725758,"about_ca_topic_score_gemma":3.166053e-8,"domain_scores_codex":[0.9989296,0.00002007085,0.0002666542,0.0002315429,0.0003834916,0.0001686153],"domain_scores_gemma":[0.9989704,0.0002910917,0.0003098396,0.0000850547,0.0003161269,0.00002750011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008462011,0.00001740737,0.0002018071,0.00004044526,0.0000588929,8.268614e-8,0.002730283,0.08320982,0.01263649,0.8994174,0.0003347407,0.001267993],"study_design_scores_gemma":[0.0001727704,0.00006608696,0.0003374745,0.0003038012,0.000006636245,0.00000229607,0.001348608,0.9750097,0.01912484,0.00343873,0.0001002999,0.00008879635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7207681,0.00002997248,0.2344889,0.01586512,0.0007796248,0.001263251,0.000008025842,0.001800146,0.0249968],"genre_scores_gemma":[0.9736695,0.00001146,0.02568907,0.0001672746,0.00004203713,0.0001923632,0.000002629972,0.000008253243,0.0002173772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8959787,"threshold_uncertainty_score":0.3260385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1186295975928637,"score_gpt":0.3315998377887009,"score_spread":0.2129702401958372,"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."}}