{"id":"W3134001436","doi":"","title":"On the difficulty of generalizing deep reinforcement learning framework for combinatorial optimization","year":2021,"lang":"en","type":"preprint","venue":"UVic’s Research and Learning Repository (University of Victoria)","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Reinforcement learning; Computer science; Heuristics; Quadratic assignment problem; Combinatorial optimization; Graph; Artificial intelligence; Travelling salesman problem; Mathematical optimization; Optimization problem; Theoretical computer science; 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":[0.00311472,0.001653232,0.00177501,0.0006691339,0.0006223912,0.001775108,0.002167386,0.002042056,0.005448471],"category_scores_gemma":[0.01345646,0.000838066,0.001390145,0.0007881855,0.00232439,0.003811404,0.002390668,0.00592034,0.0006925417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002191678,"about_ca_system_score_gemma":0.002576574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007894972,"about_ca_topic_score_gemma":0.008926039,"domain_scores_codex":[0.9987811,0.000521031,0.00005376213,0.0002999999,0.0002192829,0.0001246356],"domain_scores_gemma":[0.9930441,0.005483552,0.0003163462,0.0005111988,0.0004112074,0.0002335596],"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":[0.00003361053,0.00005494253,0.0004131212,0.0001023759,0.00003575786,0.00006068433,0.00005444779,0.8893986,0.0003150756,0.08692143,0.002344642,0.02026539],"study_design_scores_gemma":[0.000007681976,0.00001132013,0.00004103657,0.000009310647,0.000002969381,0.000006570944,0.000006081153,0.9486416,0.00005873896,0.05074878,0.0004630413,0.00000288134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0127078,0.0006781148,0.9786096,0.002058708,0.00009571659,0.00006071424,0.0001031063,0.0003285584,0.005357598],"genre_scores_gemma":[0.6787067,0.002187513,0.3044542,0.001779658,0.0004255549,0.0005410313,0.000510109,0.00059636,0.01079883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007894972,"threshold_uncertainty_score":0.01822692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03848310886771322,"score_gpt":0.2886510004279528,"score_spread":0.2501678915602396,"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."}}