{"id":"W4410826557","doi":"10.2139/ssrn.5272328","title":"Interpretable Online Scheduling for Chemical Batch Plants with Attention Augmented Reinforcement Learning Agents","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Scheduling (production processes); Reinforcement; Computer science; Artificial intelligence; Engineering; Operations management","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":[0.0007546854,0.0008920507,0.001015962,0.0003157507,0.000400201,0.0008986232,0.001127315,0.001390084,0.002892776],"category_scores_gemma":[0.003889186,0.0005158465,0.0004447874,0.0002325433,0.0008530603,0.0007416059,0.001260408,0.001595596,0.0002626572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009181031,"about_ca_system_score_gemma":0.00120187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01123563,"about_ca_topic_score_gemma":0.01101424,"domain_scores_codex":[0.9997374,0.00008140405,0.00001390114,0.00006123183,0.00005247956,0.00005348851],"domain_scores_gemma":[0.9985321,0.0009744684,0.000169838,0.00008768505,0.0001618775,0.00007405873],"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":[0.00008967318,0.00003766303,0.0001702188,0.00002648839,0.00001081349,0.00005089563,0.00003515593,0.9850159,0.0006986829,0.003196934,0.0003279158,0.0103396],"study_design_scores_gemma":[0.000006372269,0.000009163728,0.00002550704,0.000001255859,0.000001366039,0.000001505749,0.000001686957,0.9982862,0.00007893507,0.001550873,0.00003592709,0.000001137217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1027257,0.000263564,0.8894247,0.0005249205,0.0001262217,0.00008693547,0.0001186652,0.0008530426,0.005876274],"genre_scores_gemma":[0.9661162,0.00004841748,0.03137885,0.00007236675,0.00003544472,0.00007852925,0.0000692176,0.00004705152,0.002153932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01123563,"threshold_uncertainty_score":0.02234048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007054414651572988,"score_gpt":0.2409170626854051,"score_spread":0.2338626480338321,"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."}}