{"id":"W4309345280","doi":"10.1109/smc53654.2022.9945274","title":"A Deep Averaged Reinforcement Learning Approach for the Traveling Salesman Problem","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Reinforcement learning; Travelling salesman problem; Heuristics; Forgetting; Computer science; Artificial intelligence; Convergence (economics); Generalization; Mathematical optimization; Process (computing); Machine learning; Mathematics; Algorithm","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":[0.0007555572,0.0006889123,0.0008162666,0.0003752865,0.0002888005,0.0004596168,0.001151515,0.0007151176,0.001953097],"category_scores_gemma":[0.001587784,0.0003229426,0.0004272606,0.0003034533,0.0004774345,0.0007426377,0.0006505942,0.001185891,0.0002067528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007702667,"about_ca_system_score_gemma":0.001305368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008205516,"about_ca_topic_score_gemma":0.006973672,"domain_scores_codex":[0.9996926,0.00008629121,0.00001792883,0.00007059378,0.00007815904,0.00005457125],"domain_scores_gemma":[0.9995908,0.0001657184,0.00005272217,0.00003486833,0.0001147965,0.00004116899],"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":[0.00003609238,0.00005125507,0.0004221057,0.00003455388,0.00002972408,0.00003890926,0.00002954941,0.935239,0.001252947,0.005433665,0.0006352498,0.05679695],"study_design_scores_gemma":[0.000002804089,0.00001479859,0.00002774719,0.000001305376,0.000002294737,0.000004243782,0.00000113815,0.9988558,0.0001473852,0.0008050937,0.000136064,0.000001345898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02234605,0.0003022197,0.9740521,0.0001632422,0.00005167559,0.00003966509,0.00003114658,0.0005895241,0.002424423],"genre_scores_gemma":[0.792967,0.0001976777,0.2031843,0.0001734384,0.00005123247,0.0001013265,0.00009215022,0.00007747692,0.003155421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008205516,"threshold_uncertainty_score":0.01631546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04134696800989715,"score_gpt":0.2538691343529126,"score_spread":0.2125221663430154,"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."}}