{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006864206,0.0006220989,0.001208168,0.0003890366,0.0003803771,0.0007342604,0.001862395,0.00191299,0.006053714],"category_scores_gemma":[0.002271957,0.0005168139,0.0005080734,0.0004961463,0.0006535866,0.001137457,0.001263147,0.002100626,0.0005887226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00113029,"about_ca_system_score_gemma":0.001470417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01506099,"about_ca_topic_score_gemma":0.01327037,"domain_scores_codex":[0.9997329,0.00007761358,0.00001097737,0.00007699879,0.00004507696,0.00005650726],"domain_scores_gemma":[0.9991993,0.0005356033,0.00005336248,0.0000400404,0.0001066767,0.00006490749],"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":[0.0001148254,0.0001222322,0.000571546,0.00006984529,0.00003835676,0.00006712921,0.00003358803,0.9180502,0.000616463,0.01248531,0.00343131,0.06439927],"study_design_scores_gemma":[0.00000775116,0.000008394905,0.00002977144,0.000003169901,0.000002796374,0.000003034188,0.000002202753,0.9963616,0.0000628896,0.003363267,0.0001537936,0.000001482265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04348683,0.0008270518,0.9476877,0.001212034,0.0001503839,0.00006490004,0.0002971843,0.0006911785,0.005582688],"genre_scores_gemma":[0.8458284,0.0003721053,0.1401593,0.0004419518,0.0001569552,0.000158916,0.0005174808,0.0001199417,0.01224484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01506099,"threshold_uncertainty_score":0.02994663,"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."}}