{"id":"W2923289556","doi":"","title":"A new dog learns old tricks: RL finds classic optimization algorithms","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Optimization algorithm; Algorithm; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002664274,0.0001926355,0.0001767432,0.0004695986,0.0001950593,0.0007662723,0.001055901,0.0001010262,0.004122612],"category_scores_gemma":[0.0002954765,0.0001966721,0.0001054444,0.0006416918,0.00003560618,0.0009998586,0.0002277646,0.0005148779,0.001198583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001095393,"about_ca_system_score_gemma":0.000310628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000137297,"about_ca_topic_score_gemma":0.000006273259,"domain_scores_codex":[0.9976742,0.0001837733,0.0003786669,0.0006504612,0.0008150934,0.0002978154],"domain_scores_gemma":[0.9983796,0.0002304591,0.0002240721,0.0004684504,0.0005105902,0.0001868223],"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":[0.00001404456,0.00009015739,0.004365931,0.000004623503,0.00005804302,0.000006903191,0.001626993,0.7592593,0.0002558879,0.207577,0.00234053,0.0244006],"study_design_scores_gemma":[0.0008975734,0.0001618243,0.001528435,0.00004707376,0.000004831233,0.000009516308,0.0002671394,0.9873877,0.0001141276,0.001796608,0.007555102,0.0002300575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000678296,0.000008499437,0.8744918,0.008504178,0.0008317069,0.0003184947,0.000004096541,0.0003061216,0.1148568],"genre_scores_gemma":[0.6021023,0.0001747007,0.1813392,0.0007133868,0.0002675867,0.00007548089,0.000238914,0.00004102979,0.2150473],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6931525,"threshold_uncertainty_score":0.9995791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04493808541385731,"score_gpt":0.3381104561314346,"score_spread":0.2931723707175773,"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."}}