{"id":"W3157652862","doi":"10.1016/j.knosys.2022.108489","title":"A deep reinforcement learning approach for the meal delivery problem","year":2022,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Operations research; Order (exchange); Service (business); Set (abstract data type); Process (computing); Markov process; Variety (cybernetics); Artificial intelligence; Marketing; Business; Engineering; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005174897,0.0001259779,0.0001375342,0.0001028748,0.0005053044,0.0000397684,0.0001783094,0.00003338619,0.00004624012],"category_scores_gemma":[0.000009426217,0.0001092556,0.00008831485,0.0003641207,0.00002091904,0.00004242081,0.00001115139,0.0002261173,0.000009682341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000180143,"about_ca_system_score_gemma":0.00007167184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003230782,"about_ca_topic_score_gemma":0.00003154625,"domain_scores_codex":[0.9990552,0.00005123135,0.0003505728,0.0001517346,0.0001745516,0.0002167093],"domain_scores_gemma":[0.9994545,0.0001327673,0.00004914066,0.0002027633,0.0001227906,0.00003802362],"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":[0.00001327497,0.00003827783,0.0001369469,0.0003234045,0.00005779539,2.296229e-7,0.001159814,0.9925553,0.000283924,0.003282027,0.001283634,0.0008653528],"study_design_scores_gemma":[0.0005598816,0.00006645649,0.00006689672,0.000009267706,0.00003168285,0.000001414341,0.00147465,0.9022799,0.00008044468,0.000003662029,0.09530031,0.0001254571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003072167,0.001008675,0.9843703,0.00004000901,0.0006680857,0.001672057,0.00001428988,0.000446758,0.008707644],"genre_scores_gemma":[0.994048,0.000002660133,0.0005603031,0.00002370223,0.00009112549,0.003960284,0.0002514414,0.00003300267,0.001029496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9909758,"threshold_uncertainty_score":0.4455316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02092170731942637,"score_gpt":0.2242285503242626,"score_spread":0.2033068430048362,"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."}}