Hi everyone, I’m one of the authors. Happy to answer questions about the method, evaluation setup, or reproducibility.</p>\n","updatedAt":"2026-06-01T16:45:25.933Z","author":{"_id":"635a9632674e6dfcf134cb74","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/635a9632674e6dfcf134cb74/74ceGgwWG95KH40KASYDl.jpeg","fullname":"Bibek Poudel","name":"matrix-multiply","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8430479168891907},"editors":["matrix-multiply"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/635a9632674e6dfcf134cb74/74ceGgwWG95KH40KASYDl.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.28730","authors":[{"_id":"6a1d952e808ddbc3c7d4395c","name":"Bibek Poudel","hidden":false},{"_id":"6a1d952e808ddbc3c7d4395d","name":"Sai Swaminathan","hidden":false},{"_id":"6a1d952e808ddbc3c7d4395e","name":"Weizi Li","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/635a9632674e6dfcf134cb74/SWXVrOcGFJTO6mGjdUEL3.mp4"],"publishedAt":"2026-05-27T00:00:00.000Z","submittedOnDailyAt":"2026-06-01T00:00:00.000Z","title":"AlphaTransit: Learning to Design City-scale Transit Routes","submittedOnDailyBy":{"_id":"635a9632674e6dfcf134cb74","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/635a9632674e6dfcf134cb74/74ceGgwWG95KH40KASYDl.jpeg","isPro":false,"fullname":"Bibek Poudel","user":"matrix-multiply","type":"user","name":"matrix-multiply"},"summary":"Designing a transit network requires many sequential route extension decisions, but their quality is often visible only after the full network is assembled. This delayed-feedback challenge lies at the heart of the Transit Route Network Design Problem (TRNDP), where route interactions can be deceptive: an extension that appears useful locally can create transfer bottlenecks, produce redundant overlap, or reduce overall throughput. To guide route construction under delayed simulator feedback, we introduce AlphaTransit, a search-based planning framework for cityscale bus network design. AlphaTransit couples Monte Carlo Tree Search (MCTS) with a neural policy-value network: the policy proposes route extensions, the value estimates downstream design quality, and search uses these predictions to refine each decision. This provides decision-time lookahead during route construction without running simulator rollouts inside the search tree. We evaluate AlphaTransit on a new Bloomington TRNDP benchmark with realistic road topology and censusderived demand, under mixed and full transit demand settings. In the Bloomington network, AlphaTransit attains the highest service rate in both demand settings, reaching 54.6% and 82.1%, respectively. Relative to reinforcement learning without search, these correspond to 9.9% and 11.4% service rate gains; relative to MCTS without learned guidance, they correspond to 2.5% and 11.2% gains. These results suggest that coupling learned guidance with MCTS is more effective than using either approach alone for transit network design. Our code and data are publicly available in https://github.com/poudel-bibek/AlphaTransit.","upvotes":1,"discussionId":"6a1d952f808ddbc3c7d4395f","projectPage":"https://alphatransit.app/","githubRepo":"https://github.com/poudel-bibek/AlphaTransit","githubRepoAddedBy":"user","ai_summary":"AlphaTransit combines Monte Carlo Tree Search with neural policy-value networks to optimize bus route design by predicting downstream quality and enabling lookahead decisions without simulator rollouts.","ai_keywords":["Monte Carlo Tree Search","neural policy-value network","route extensions","transit network design","delayed feedback","service rate","reinforcement learning"],"githubStars":4},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"666b144b590bb29565b022e9","avatarUrl":"/avatars/7cb473e1812173a9157d989949df74e2.svg","isPro":false,"fullname":"John Loverich","user":"john-glodon","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.28730.md"}">
AlphaTransit: Learning to Design City-scale Transit Routes
Abstract
AlphaTransit combines Monte Carlo Tree Search with neural policy-value networks to optimize bus route design by predicting downstream quality and enabling lookahead decisions without simulator rollouts.
AI-generated summary
Designing a transit network requires many sequential route extension decisions, but their quality is often visible only after the full network is assembled. This delayed-feedback challenge lies at the heart of the Transit Route Network Design Problem (TRNDP), where route interactions can be deceptive: an extension that appears useful locally can create transfer bottlenecks, produce redundant overlap, or reduce overall throughput. To guide route construction under delayed simulator feedback, we introduce AlphaTransit, a search-based planning framework for cityscale bus network design. AlphaTransit couples Monte Carlo Tree Search (MCTS) with a neural policy-value network: the policy proposes route extensions, the value estimates downstream design quality, and search uses these predictions to refine each decision. This provides decision-time lookahead during route construction without running simulator rollouts inside the search tree. We evaluate AlphaTransit on a new Bloomington TRNDP benchmark with realistic road topology and censusderived demand, under mixed and full transit demand settings. In the Bloomington network, AlphaTransit attains the highest service rate in both demand settings, reaching 54.6% and 82.1%, respectively. Relative to reinforcement learning without search, these correspond to 9.9% and 11.4% service rate gains; relative to MCTS without learned guidance, they correspond to 2.5% and 11.2% gains. These results suggest that coupling learned guidance with MCTS is more effective than using either approach alone for transit network design. Our code and data are publicly available in https://github.com/poudel-bibek/AlphaTransit.
Community
Hi everyone, I’m one of the authors. Happy to answer questions about the method, evaluation setup, or reproducibility.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.28730 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.