{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003387086,0.002172142,0.001008584,0.001560785,0.0007424965,0.001368213,0.003096447,0.001647177,0.00987605],"category_scores_gemma":[0.01309727,0.0004721903,0.001098342,0.002538079,0.001015923,0.001684455,0.001467221,0.002406222,0.002224465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001836809,"about_ca_system_score_gemma":0.003249163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008493174,"about_ca_topic_score_gemma":0.01558094,"domain_scores_codex":[0.9977995,0.0007838171,0.0001374996,0.0003350393,0.0006178758,0.0003262862],"domain_scores_gemma":[0.9929558,0.004367524,0.0002908819,0.001036479,0.001010457,0.000338906],"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":[0.0007155624,0.001392788,0.005176036,0.001721247,0.00026572,0.000219882,0.00008535778,0.6908214,0.002601238,0.02640002,0.1501246,0.120476],"study_design_scores_gemma":[0.000409626,0.0004413992,0.001667607,0.0001295279,0.0000476518,0.00008803292,0.00007730152,0.9425912,0.003792326,0.02178524,0.02893181,0.000038389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3511957,0.01116503,0.3501393,0.006254864,0.002111106,0.001892924,0.03638874,0.04829106,0.1925613],"genre_scores_gemma":[0.5636865,0.002230102,0.3692976,0.001835051,0.0002096097,0.001887171,0.04027677,0.005522226,0.01505499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00987605,"threshold_uncertainty_score":0.03303868,"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."}}