{"id":"W4313680365","doi":"10.2139/ssrn.4319327","title":"Deep Reinforcement Learning for Machine Scheduling: Methodology, the State-of-The-Art, and Future Directions","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Scheduling (production processes); Machine learning; Operations research; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001577582,0.00009805211,0.0001168126,0.00008306516,0.0003591388,0.00002870232,0.000134475,0.00004351814,0.000006481468],"category_scores_gemma":[0.0001337432,0.00006330171,0.00008122787,0.0003178764,0.00003264124,0.00005109221,0.00002476088,0.00102288,0.000003140378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000121952,"about_ca_system_score_gemma":0.0001192005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005379534,"about_ca_topic_score_gemma":0.00009702734,"domain_scores_codex":[0.9988486,0.00008366354,0.0002045525,0.00008061324,0.0001069774,0.0006755909],"domain_scores_gemma":[0.9995605,0.0001836663,0.00007108743,0.00009469451,0.00005576271,0.00003425286],"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":[0.000009712877,0.0000023272,0.0000816626,0.000008634473,0.0001223759,1.14497e-7,0.0003859909,0.9479824,0.0000656382,0.002792818,0.00002671604,0.04852165],"study_design_scores_gemma":[0.0003793288,0.00007139218,0.0001033605,0.000008776421,0.00004311441,0.00007536947,0.001404058,0.976081,0.0002007896,0.01398615,0.0075555,0.00009120515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01174004,0.007086997,0.978178,0.001668934,0.0008457207,0.0001814357,7.503936e-7,0.0001476968,0.0001504892],"genre_scores_gemma":[0.7898229,0.1135932,0.08379232,0.0002191745,0.002051916,0.0001273708,0.00004651009,0.0002237848,0.01012279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8943856,"threshold_uncertainty_score":0.4443963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588945352918465,"score_gpt":0.2622895898932567,"score_spread":0.246400136364072,"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."}}