{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003987417,0.0001596174,0.0001484893,0.00009814147,0.0003484229,0.0001315367,0.000262892,0.00004103461,0.0001804462],"category_scores_gemma":[0.000009937979,0.0001483819,0.00005480344,0.0001175906,0.00003435107,0.00005569989,0.00002075038,0.0003565408,0.000004677055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001035245,"about_ca_system_score_gemma":0.00003063671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005313172,"about_ca_topic_score_gemma":0.00003757375,"domain_scores_codex":[0.9987261,0.00004037851,0.0004159758,0.0002263987,0.0004096629,0.0001814724],"domain_scores_gemma":[0.9994901,0.00008578665,0.00009444232,0.0001459742,0.0001416994,0.00004202739],"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":[0.00002577344,0.00002810066,0.0001559058,0.00007303798,0.0001234038,0.00000106798,0.001472416,0.8608704,0.0005805626,0.1352892,0.0004378513,0.0009422048],"study_design_scores_gemma":[0.0005541577,0.00008739528,0.0004063736,0.00002046849,0.00002976031,0.00001002684,0.003505809,0.9626601,0.00006159157,0.0001901674,0.03228529,0.0001888103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06334584,0.0003934338,0.855496,0.0006664166,0.002772121,0.002703036,0.0001556626,0.0004200705,0.07404742],"genre_scores_gemma":[0.9935671,0.0001304139,0.0003227464,0.0001038347,0.0001077823,0.0009219557,0.0003087073,0.00002647078,0.004511003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9302213,"threshold_uncertainty_score":0.605084,"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."}}