{"id":"W4285900278","doi":"10.1007/s12083-022-01353-0","title":"DHL: Deep reinforcement learning-based approach for emergency supply distribution in humanitarian logistics","year":2022,"lang":"en","type":"article","venue":"Peer-to-Peer Networking and Applications","topic":"Facility Location and Emergency Management","field":"Business, Management and Accounting","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Humanitarian Logistics; Distribution (mathematics); Operations research; Emergency management; Resource (disambiguation); Business; Supply chain; Supply and demand; Computer science; Process (computing); Risk analysis (engineering); Resource distribution; Operations management; Resource allocation; Economics; Engineering; Industrial organization; Marketing; Economic growth; Microeconomics; 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":[0.0008782052,0.0008501987,0.0009877604,0.0005081419,0.0003734451,0.0006647795,0.001818651,0.001346144,0.004873819],"category_scores_gemma":[0.00178241,0.0004578802,0.0004741261,0.0004505989,0.0004605657,0.0009666156,0.00114308,0.00200582,0.0008094508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107175,"about_ca_system_score_gemma":0.001464285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01851981,"about_ca_topic_score_gemma":0.01751978,"domain_scores_codex":[0.9997248,0.00008625112,0.00001235983,0.00006998571,0.00004897462,0.00005754996],"domain_scores_gemma":[0.9992977,0.0004015309,0.00004311045,0.00004162849,0.0001519888,0.00006389956],"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":[0.0001524009,0.000223262,0.00113843,0.00008946987,0.00006489454,0.00008143373,0.00004395241,0.8282823,0.001184913,0.002963522,0.007778349,0.157997],"study_design_scores_gemma":[0.000004865881,0.00001033737,0.00003045858,0.00000203721,0.000002008618,0.000002349396,0.000002981974,0.9990928,0.0001277408,0.0005633947,0.0001597927,0.000001178433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04421458,0.00119024,0.9439372,0.0008788427,0.0002841589,0.0001109686,0.0004254798,0.004286421,0.004672072],"genre_scores_gemma":[0.8281101,0.0003172013,0.158975,0.0006448008,0.0001274927,0.0001777099,0.0007857772,0.0002567451,0.01060517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01851981,"threshold_uncertainty_score":0.03682405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03062303755965068,"score_gpt":0.2562055703969894,"score_spread":0.2255825328373387,"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."}}