{"id":"W4408810302","doi":"10.1021/acs.iecr.4c04900","title":"Recurrent Reinforcement Learning Strategy with a Parameterized Agent for Online Scheduling of a State Task Network Under Uncertainty","year":2025,"lang":"en","type":"article","venue":"Industrial & Engineering Chemistry Research","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Reinforcement learning; Parameterized complexity; Computer science; Scheduling (production processes); Task (project management); Reinforcement; Artificial intelligence; Error-driven learning; State (computer science); Machine learning; Mathematical optimization; Algorithm; Psychology; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000841081,0.0002613436,0.0003747965,0.0001394263,0.000109756,0.00008853333,0.0002657992,0.0002228942,0.00002759197],"category_scores_gemma":[0.0003888691,0.0002580755,0.00008601106,0.0009485752,0.00006227557,0.00005798606,0.00006869667,0.001112117,9.790153e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002886158,"about_ca_system_score_gemma":0.0002688866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002042566,"about_ca_topic_score_gemma":0.000001725274,"domain_scores_codex":[0.9979964,0.00003750807,0.0005252532,0.0003123868,0.000427205,0.0007012562],"domain_scores_gemma":[0.9987856,0.0004270833,0.00006342347,0.0002810369,0.0003125441,0.0001302772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002408515,0.00003173529,0.00001808178,0.0003165232,0.0002134535,0.00000248655,0.00004417467,0.9664263,0.02840726,0.00002209788,0.0001077487,0.004169278],"study_design_scores_gemma":[0.002143912,0.0001383537,0.000006222999,0.0007048627,0.00002723396,0.000001591871,0.0001463915,0.9597549,0.03525103,0.00002456699,0.001564746,0.0002362263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.811987,0.0007017825,0.1846915,0.0001273254,0.0005418677,0.001122146,0.00004908792,0.0005151303,0.0002641767],"genre_scores_gemma":[0.9885144,0.0001289002,0.009773868,0.0000059637,0.0004157374,0.0001988923,0.0002423724,0.0000711454,0.0006487346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1765274,"threshold_uncertainty_score":0.9999871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07084368239796389,"score_gpt":0.3286161707403337,"score_spread":0.2577724883423698,"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."}}