{"id":"W3216891387","doi":"10.1109/etfa45728.2021.9613611","title":"Embedding Reinforcement Learning in Simulation","year":2021,"lang":"en","type":"article","venue":"","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Embedding; Computer science; Field (mathematics); Visualization; Domain (mathematical analysis); Truck; Discrete event simulation; Artificial intelligence; Industrial engineering; Simulation; Engineering","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":[0.00004703747,0.00003622276,0.00004178338,0.00003795302,0.00001582176,0.0000189817,0.00001482992,0.00002380315,0.0003472735],"category_scores_gemma":[0.00004130457,0.00004022825,0.00001108169,0.0001403893,0.000001522551,0.00005428306,0.000006783279,0.00006876729,0.00002878751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000282846,"about_ca_system_score_gemma":0.000006069548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001595744,"about_ca_topic_score_gemma":0.000002162238,"domain_scores_codex":[0.9997212,0.000006375802,0.00009349328,0.00005124142,0.0000529452,0.00007472172],"domain_scores_gemma":[0.9998898,0.00002653978,0.000004952847,0.00004235531,0.00001966963,0.00001667378],"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":[2.92123e-7,0.000001423026,0.0002568871,0.00000439502,0.000002182998,0.000002739066,0.0001205083,0.9969437,0.00008127005,0.00007203937,0.000006276461,0.002508312],"study_design_scores_gemma":[0.0001285188,0.000001972112,0.00009902279,0.000009685927,8.808806e-7,5.266866e-7,0.0001651582,0.9975579,0.001558245,0.000008936413,0.0004171795,0.00005190695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03297802,0.0000669161,0.9458719,0.0000254078,0.0001382222,0.00002304134,3.399188e-8,0.0002930262,0.02060346],"genre_scores_gemma":[0.962907,0.00001503856,0.03560814,0.00002825508,0.00002303015,0.000001738342,0.000009354216,0.000007787767,0.001399673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.929929,"threshold_uncertainty_score":0.3802402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.012930293854495,"score_gpt":0.2581033303218984,"score_spread":0.2451730364674034,"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."}}