{"id":"W2795943763","doi":"10.1007/978-3-319-89656-4_36","title":"Automated Scheduling: Reinforcement Learning Approach to Algorithm Policy Learning","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Reinforcement learning; Scheduling (production processes); Automated planning and scheduling; Artificial intelligence; Machine learning; Mathematical optimization; Mathematics","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":[0.0006016677,0.0005323282,0.0004514226,0.001283179,0.0003062789,0.0003522765,0.0008095482,0.0003662275,0.00005194211],"category_scores_gemma":[0.0002028124,0.0005471883,0.0000905451,0.0009045729,0.0002432919,0.0001707655,0.0003412514,0.001179092,0.0001698822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004849625,"about_ca_system_score_gemma":0.0002442824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000014299,"about_ca_topic_score_gemma":0.000001503061,"domain_scores_codex":[0.9972406,0.00002229922,0.000488033,0.0008295117,0.00070801,0.0007115698],"domain_scores_gemma":[0.998831,0.0001016219,0.0001156169,0.0004489548,0.0002365457,0.0002662406],"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":[0.000001459895,0.000004682601,0.000002844219,0.00002564872,0.0000140961,0.000004131324,0.0009273613,0.8471231,0.00001724024,0.0001242619,0.000009675567,0.1517455],"study_design_scores_gemma":[0.0001913364,0.0001117647,0.000004622148,0.0002433263,0.000008269579,0.00002307768,0.000001539716,0.9965271,0.0003622688,0.0004697697,0.001451285,0.0006056564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005168396,0.0001344579,0.9851673,0.00006909832,0.0008820622,0.000294708,0.000001168869,0.001851429,0.01154815],"genre_scores_gemma":[0.02058272,0.00004054528,0.9762351,0.0003257882,0.001355292,0.00001378268,0.00003788011,0.0001164869,0.001292389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1511398,"threshold_uncertainty_score":0.999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01364201100464725,"score_gpt":0.2434536808135347,"score_spread":0.2298116698088875,"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."}}