{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001761799,0.0009443028,0.001151716,0.0006309091,0.0004187989,0.001334797,0.002110841,0.001319115,0.005077276],"category_scores_gemma":[0.006925689,0.0006602687,0.0006561868,0.0009898791,0.0009671551,0.001315918,0.00103431,0.002790525,0.001054456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001398162,"about_ca_system_score_gemma":0.001726194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004055786,"about_ca_topic_score_gemma":0.00389414,"domain_scores_codex":[0.9988701,0.0005568614,0.00004873468,0.0001593578,0.000289064,0.00007591627],"domain_scores_gemma":[0.9973575,0.001864925,0.0001143484,0.0002772708,0.0003183883,0.00006746103],"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":[0.00007218813,0.00008666344,0.0002029643,0.0001222668,0.00004279331,0.00002247764,0.00005242856,0.7870355,0.000841104,0.04532807,0.004889648,0.1613038],"study_design_scores_gemma":[0.000005917645,0.000007624313,0.00002272308,0.000006198025,0.000002829956,0.000004268381,0.000002400247,0.9838516,0.0002130889,0.01509475,0.0007859039,0.000002639255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002059312,0.0003963918,0.9939402,0.0001508579,0.00008432354,0.00002567087,0.00002596911,0.0005174258,0.00279982],"genre_scores_gemma":[0.3198697,0.001006616,0.6689166,0.0002212629,0.0003000195,0.0002933771,0.0002182347,0.0004347477,0.008739484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005077276,"threshold_uncertainty_score":0.01698518,"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."}}