{"id":"W4387427604","doi":"10.48550/arxiv.2310.03195","title":"Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Machine learning; Scheduling (production processes); Job shop scheduling; Heuristics; Interpretability; Scalability; Mathematical optimization; Schedule","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":[0.0003880268,0.0001916461,0.0002211651,0.0001028182,0.0002403359,0.00002812959,0.0002943003,0.0001560136,0.00001413136],"category_scores_gemma":[0.000110336,0.000157299,0.0001495244,0.000335024,0.00008682603,0.00004290384,0.0002847317,0.0005965758,0.000005412463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006074801,"about_ca_system_score_gemma":0.00002997593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003369699,"about_ca_topic_score_gemma":0.00006408719,"domain_scores_codex":[0.9991809,0.0001125408,0.0001783968,0.0002894991,0.00004810307,0.0001905648],"domain_scores_gemma":[0.999062,0.0003319711,0.000118256,0.000340631,0.00009311576,0.00005400951],"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":[0.00001352522,0.000004262611,0.0002528677,0.00009151059,0.0001532057,0.00000146425,0.0003614657,0.9967311,0.000005940492,0.0010883,0.00003379337,0.001262538],"study_design_scores_gemma":[0.00025857,0.00001589159,0.0002035633,0.00003374023,0.0001284505,0.000001422745,0.0003104483,0.9937854,0.0001024896,0.002228749,0.002766982,0.000164242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01398949,0.0005887288,0.9827715,0.0002184285,0.001510151,0.0003880797,0.000008332988,0.0003105265,0.0002147371],"genre_scores_gemma":[0.8994606,0.01064594,0.0781463,0.00007570845,0.000496252,0.00002132007,0.0001445058,0.0001632186,0.01084612],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9046252,"threshold_uncertainty_score":0.6414469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07368779149999558,"score_gpt":0.2219055828409262,"score_spread":0.1482177913409306,"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."}}