{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002573017,0.0002393944,0.0004956634,0.00031303,0.001577366,0.0004243678,0.001396539,0.0004024704,0.00007703615],"category_scores_gemma":[0.00310043,0.0002401474,0.0001841684,0.0006775127,0.0003519026,0.0002057495,0.002059536,0.002552307,0.000001817514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002144928,"about_ca_system_score_gemma":0.0004676268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002186547,"about_ca_topic_score_gemma":0.000002449103,"domain_scores_codex":[0.9949586,0.001737311,0.0003782189,0.0007759338,0.001663372,0.0004865612],"domain_scores_gemma":[0.9929968,0.003194688,0.0005280671,0.0007929004,0.002278047,0.0002095745],"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":[0.000141023,0.0001240722,0.0002026462,0.0003422578,0.0001803379,0.0000210563,0.004377068,0.9519241,0.0003459773,0.04145229,0.00017992,0.0007092861],"study_design_scores_gemma":[0.0006234566,0.0007047125,0.0001727897,0.0004144807,0.00002423193,0.000002940298,0.002006479,0.992619,0.0004613846,0.00186776,0.000874366,0.0002283555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01884124,0.0003189075,0.9776217,0.0003782938,0.001117776,0.0007564069,0.000001595035,0.00006483308,0.0008992149],"genre_scores_gemma":[0.7807068,0.0008818763,0.2155637,0.000009402292,0.0004230298,0.00001557005,0.00009632893,0.0000421105,0.00226123],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.762058,"threshold_uncertainty_score":0.9997488,"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."}}