{"id":"W4412877155","doi":"10.1145/3711896.3737433","title":"RL4CO: An Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","year":2025,"lang":"en","type":"article","venue":"","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Benchmark (surveying); Computer science; Artificial intelligence; Combinatorial optimization; Machine learning; Algorithm; Geography; Cartography","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":[0.0001063937,0.0000993283,0.0001068992,0.00007392695,0.000112194,0.00005784251,0.00007152927,0.00007353684,0.0001310348],"category_scores_gemma":[0.00008871088,0.0001041214,0.00003442935,0.0001749237,0.000009765093,0.0001260507,0.00001234735,0.00008099688,0.000003853044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004817854,"about_ca_system_score_gemma":0.0000195942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004159128,"about_ca_topic_score_gemma":5.111357e-7,"domain_scores_codex":[0.9994578,0.00001161924,0.0001762883,0.0001272745,0.00007730696,0.0001496502],"domain_scores_gemma":[0.9996117,0.00005187421,0.00001869707,0.0001134521,0.0001597142,0.00004459819],"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":[0.0000105156,0.0000080478,0.00002034054,0.00001767155,0.00002181349,1.706234e-7,0.00006541082,0.9906685,0.00002652807,0.00712092,0.0006330675,0.001407002],"study_design_scores_gemma":[0.0007431898,0.0000521855,0.00001271739,0.00001455066,0.00001597169,2.519961e-7,0.0001789271,0.9963101,0.0009647817,0.0002291327,0.001360443,0.0001178007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005759803,0.0000496114,0.9834452,0.00005054161,0.001571323,0.0002311461,5.212664e-7,0.0004344969,0.01364118],"genre_scores_gemma":[0.4457105,0.00009235454,0.5492816,0.0002819273,0.0002925905,0.0001237877,0.0003733691,0.00004701615,0.003796884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4451345,"threshold_uncertainty_score":0.4245948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007863841065880686,"score_gpt":0.2398873296377925,"score_spread":0.2320234885719118,"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."}}