{"id":"W4394708860","doi":"10.48550/arxiv.2404.05894","title":"Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Heuristics; Computer science; Artificial intelligence; Reinforcement; Machine learning; Engineering; Structural engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001566888,0.001478227,0.001093076,0.0009712822,0.0004910341,0.000963301,0.001376466,0.001191097,0.003076993],"category_scores_gemma":[0.006809408,0.0007664166,0.0006300429,0.0007643197,0.001404157,0.00149845,0.001035175,0.001698409,0.0003345757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002243573,"about_ca_system_score_gemma":0.00220026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009976409,"about_ca_topic_score_gemma":0.01615275,"domain_scores_codex":[0.9994535,0.0001997604,0.00002842854,0.0001332064,0.00008986955,0.00009528495],"domain_scores_gemma":[0.9969163,0.002216579,0.00027634,0.0001773135,0.0002743854,0.0001391113],"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":[0.00003349253,0.00003590542,0.0005182116,0.00003942558,0.00002042236,0.00002437298,0.00002701398,0.9772298,0.0003067613,0.004871559,0.0006480015,0.01624501],"study_design_scores_gemma":[0.00001084397,0.00001463887,0.00003859216,0.000006344039,0.000005153625,0.000003586006,0.000006634245,0.9956131,0.0001396502,0.003965348,0.0001941449,0.000001937528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06982575,0.0009113515,0.9219779,0.0006766992,0.00007631751,0.0001173233,0.0001416453,0.0009163238,0.005356722],"genre_scores_gemma":[0.8336518,0.0003103946,0.1633254,0.0002620447,0.00003650536,0.0001516633,0.0002079566,0.0001430508,0.001911193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009976409,"threshold_uncertainty_score":0.01983672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04441041525543953,"score_gpt":0.202240706019915,"score_spread":0.1578302907644755,"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."}}