{"id":57,"date":"2023-12-15T23:54:17","date_gmt":"2023-12-15T23:54:17","guid":{"rendered":"https:\/\/labs.engineering.asu.edu\/hw\/?page_id=57"},"modified":"2026-06-11T00:17:58","modified_gmt":"2026-06-11T00:17:58","slug":"research","status":"publish","type":"page","link":"https:\/\/labs.engineering.asu.edu\/hw\/research\/","title":{"rendered":"Research"},"content":{"rendered":"<div class=\"uds-hero-sm alignfull has-btn-row \" style=\"margin-bottom:var(--wp--preset--spacing--uds-size-8);\"><div class=\"hero-overlay\"><\/div><img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"498\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/Untitled.png\" class=\"hero\" alt=\"\" srcset=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/Untitled.png 1920w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/Untitled-300x78.png 300w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/Untitled-1024x266.png 1024w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/Untitled-768x199.png 768w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/Untitled-1536x398.png 1536w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" \/><div class=\"acf-innerblocks-container\">\n\n\n\n<h1 class=\"wp-block-heading has-white-color has-text-color\"><\/h1>\n\n\n\n<div class=\"wp-block-group content is-layout-flow wp-block-group-is-layout-flow\">\n<p class=\"has-white-color has-text-color wp-block-paragraph\">Pioneering data-driven algorithms to make actionable actions in the real world.<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-buttons btn-row is-layout-flex wp-block-buttons-is-layout-flex\"><\/div>\n\n<\/div><\/div>\n\n<p hidden> <a href=\"https:\/\/clustrmaps.com\/site\/1bxvy\"  title=\"Visit tracker\"><img decoding=\"async\" src=\"\/\/www.clustrmaps.com\/map_v2.png?d=OEriF3wFbrFtJagZkiTpWYopwUKT4dfbW62v-yLg870&#038;cl=ffffff\" \/><\/a><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading has-text-align-center is-style-lead\"><strong><strong>Open Source \/ Software<\/strong><\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Our group values practical and reproducible research. Below are open-source libraries, benchmarks, and tools built by the DaRL group and our collaborators, spanning reinforcement learning for transportation, large-model agents, and spatio-temporal data mining. For the full list of repositories, see our GitHub organization<\/p>\n\n\n\n<!-- ============================================================\n     Open Source \/ Software  \u2014  drop into a Gutenberg \"Custom HTML\"\n     block placed at the very top of the Research page\n     (above the \"Generative AI\" heading).\n     Self-contained: inline CSS plus a small JS snippet that fetches\n     star count and last-pushed date from the GitHub API for any\n     card with a data-repo attribute.  Results are cached in the\n     visitor's localStorage for 6 hours to keep API usage low.\n     ============================================================ -->\n\n<style>\n  .os-wrap { font-family: inherit; color: #222; margin: 0 0 36px 0; }\n  .os-wrap h2.os-title {\n    color: #8C1D40; border-bottom: 2px solid #FFC627;\n    display: inline-block; padding-bottom: 4px;\n    margin: 0 0 14px 0;\n  }\n  .os-intro { margin: 0 0 18px 0; line-height: 1.55; font-size: 1rem; }\n  .os-grid {\n    display: grid;\n    grid-template-columns: repeat(auto-fill, minmax(320px, 1fr));\n    gap: 16px;\n  }\n  .os-card {\n    border: 1px solid #e5e5e5;\n    border-top: 3px solid #FFC627;\n    border-radius: 10px;\n    padding: 16px 18px;\n    background: #fff;\n    display: flex; flex-direction: column;\n  }\n  .os-card h3 {\n    font-size: 1.08rem; font-weight: 700; margin: 0 0 6px 0;\n    color: #222;\n  }\n  .os-role {\n    display: inline-block; font-size: .78rem; font-weight: 700;\n    padding: 2px 9px; border-radius: 999px; margin-bottom: 8px;\n    background: #fff2f2; color: #8C1D40; border: 1px solid #e7bcbc;\n    align-self: flex-start;\n  }\n  .os-role.core { background:#f2f6ff; color:#1f4b99; border-color:#bfd0ee; }\n  .os-role.contrib { background:#f5f5f5; color:#555; border-color:#ddd; }\n  .os-meta {\n    color: #555; font-size: .88rem; margin-bottom: 8px;\n    min-height: 1.3em;\n  }\n  .os-card p { font-size: .95rem; line-height: 1.5; margin: 0 0 12px 0; flex-grow: 1; }\n  .os-links { margin-bottom: 8px; }\n  .os-links a {\n    margin-right: 12px; font-size: .9rem;\n    text-decoration: none; color: #8C1D40;\n    white-space: nowrap;\n  }\n  .os-links a:hover { text-decoration: underline; }\n  .os-tags span {\n    display: inline-block; background: #f1f1f1; color: #444;\n    border: 1px solid #ddd; border-radius: 999px;\n    padding: 2px 10px; font-size: .78rem;\n    margin: 0 6px 6px 0;\n  }\n  .os-meta .gh-updated { color: #888; }\n<\/style>\n\n<div class=\"os-wrap\" id=\"os-section\">\n  <div class=\"os-grid\">\n\n    <!-- CityFlow -->\n    <div class=\"os-card\" data-repo=\"cityflow-project\/CityFlow\">\n      <h3>CityFlow<\/h3>\n      <div class=\"os-meta\">Traffic Simulator \u00b7 WWW&#8217;19<\/div>\n      <p>A multi-agent reinforcement-learning environment for\n         large-scale city traffic scenarios, orders of magnitude faster\n         than SUMO for training RL-based signal control.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/cityflow-project\/CityFlow\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/cityflow.readthedocs.io\/\" target=\"_blank\" rel=\"noopener\">\ud83d\udcd8 Docs<\/a>\n        <a href=\"https:\/\/arxiv.org\/abs\/1905.05217\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>Simulator<\/span><span>MARL<\/span><span>Traffic<\/span><\/div>\n    <\/div>\n\n    <!-- Honor of Kings Arena -->\n    <div class=\"os-card\" data-repo=\"tencent-ailab\/hok_env\">\n      <h3>Honor of Kings Arena<\/h3>\n      <div class=\"os-meta\">MARL Benchmark \u00b7 NeurIPS&#8217;22 D&amp;B<\/div>\n      <p>A competitive multi-agent reinforcement-learning environment\n         built on Tencent&#8217;s Honor of Kings MOBA game, designed to\n         benchmark generalization across heroes, lineups, and opponents.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/tencent-ailab\/hok_env\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/aiarena.tencent.com\/aiarena\/en\/open-gamecore\" target=\"_blank\" rel=\"noopener\">\ud83c\udf10 Site<\/a>\n        <a href=\"https:\/\/arxiv.org\/abs\/2209.08483\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>MARL<\/span><span>Game AI<\/span><span>Benchmark<\/span><\/div>\n    <\/div>\n\n    <!-- Instructional Agents -->\n    <div class=\"os-card\" data-repo=\"DaRL-GenAI\/instructional_agents\">\n      <h3>Instructional Agents<\/h3>\n      <div class=\"os-meta\">GenAI for Education \u00b7 EACL&#8217;26 Main<\/div>\n      <p>A multi-agent LLM system that reduces teaching-faculty workload\n         by automating instructional design \u2014 lecture plans, slides,\n         quizzes, and course material generation.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/DaRL-GenAI\/instructional_agents\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>LLM Agents<\/span><span>Education<\/span><span>EdTech<\/span><\/div>\n    <\/div>\n\n    <!-- IntelliLight -->\n    <div class=\"os-card\" data-repo=\"wingsweihua\/IntelliLight\">\n      <h3>IntelliLight<\/h3>\n      <div class=\"os-meta\">Traffic Signal Control \u00b7 KDD&#8217;18<\/div>\n      <p>A reinforcement-learning approach for intelligent traffic-light\n         control \u2014 one of the earliest deep-RL methods for adaptive\n         signal control on real-world road networks.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/wingsweihua\/IntelliLight\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3220096\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>RL<\/span><span>Traffic Signal<\/span><\/div>\n    <\/div>\n\n    <!-- RL_signals -->\n    <div class=\"os-card\" data-repo=\"traffic-signal-control\/RL_signals\">\n      <h3>RL_Signals<\/h3>\n      <div class=\"os-meta\">Community Resource<\/div>\n      <p>A curated hub of papers, datasets, simulators, and tutorials\n         covering reinforcement learning for traffic signal control \u2014\n         the go-to reading list for newcomers to the area.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/traffic-signal-control\/RL_signals\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/traffic-signal-control.github.io\/\" target=\"_blank\" rel=\"noopener\">\ud83c\udf10 Website<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>RL<\/span><span>Traffic Signal<\/span><span>Awesome List<\/span><\/div>\n    <\/div>\n\n    <!-- LibSignal -->\n    <div class=\"os-card\" data-repo=\"DaRL-LibSignal\/LibSignal\">\n      <h3>LibSignal<\/h3>\n      <div class=\"os-meta\">Traffic Signal Control \u00b7 MLJ<\/div>\n      <p>A unified open library for traffic signal control with\n         reproducible RL baselines across simulators (CityFlow, SUMO),\n         standardized benchmarks, and cross-simulator evaluation.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/DaRL-LibSignal\/LibSignal\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/darl-libsignal.github.io\/\" target=\"_blank\" rel=\"noopener\">\ud83d\udcd8 Docs<\/a>\n        <a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06412-y\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>RL<\/span><span>Benchmark<\/span><span>Traffic Signal<\/span><\/div>\n    <\/div>\n\n    <!-- PyDimension -->\n    <div class=\"os-card\" data-repo=\"xiaoyuxie-vico\/PyDimension\">\n      <h3>PyDimension<\/h3>\n      <div class=\"os-meta\">Scientific ML \u00b7 Nature Communications&#8217;22<\/div>\n      <p>Dimensionless learning \u2014 data-driven discovery of dimensionless\n         numbers and scaling laws from scarce experimental measurements,\n         combining physics priors with sparse regression.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/xiaoyuxie-vico\/PyDimension\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/xiaoyuxie.top\/PyDimension-Book\/intro.html\" target=\"_blank\" rel=\"noopener\">\ud83d\udcd8 Book<\/a>\n        <a href=\"https:\/\/www.nature.com\/articles\/s41467-022-35084-w\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>Scientific ML<\/span><span>Physics<\/span><span>Discovery<\/span><\/div>\n    <\/div>\n\n    <!-- PromptGAT -->\n    <div class=\"os-card\" data-repo=\"DaRL-LibSignal\/PromptGAT\">\n      <h3>PromptGAT<\/h3>\n      <div class=\"os-meta\">Sim-to-Real Transfer \u00b7 AAAI&#8217;24<\/div>\n      <p>Prompt-to-Transfer: closing the sim-to-real gap for traffic\n         signal control by conditioning a grounded action transformer\n         on natural-language prompts.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/DaRL-LibSignal\/PromptGAT\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/30180\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>Sim-to-Real<\/span><span>Prompt Learning<\/span><span>Traffic<\/span><\/div>\n    <\/div>\n\n    <!-- CoMAL -->\n    <div class=\"os-card\" data-repo=\"Hyan-Yao\/CoMAL\">\n      <h3>CoMAL<\/h3>\n      <div class=\"os-meta\">Multi-Agent LLM \u00b7 SDM&#8217;25<\/div>\n      <p>Collaborative Multi-Agent Large Language Models for\n         mixed-autonomy traffic \u2014 coordinating CAVs and human-driven\n         vehicles via LLM-based negotiation and planning.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/Hyan-Yao\/CoMAL\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/co-mal.vercel.app\" target=\"_blank\" rel=\"noopener\">\ud83c\udf10 Demo<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>Multi-Agent LLM<\/span><span>Mixed-Autonomy<\/span><span>Traffic<\/span><\/div>\n    <\/div>\n\n    <!-- CityFlowER -->\n    <div class=\"os-card\" data-repo=\"cityflow-project\/CityFlowER\">\n      <h3>CityFlowER<\/h3>\n      <div class=\"os-meta\">Traffic Simulator<\/div>\n      <p>An efficient and realistic traffic simulator with embedded\n         machine-learning vehicle-behavior models, bridging the gap\n         between rule-based speed and data-driven realism.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/cityflow-project\/CityFlowER\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/arxiv.org\/abs\/2402.06127\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>Simulator<\/span><span>Embedded ML<\/span><span>Traffic<\/span><\/div>\n    <\/div>\n\n    <!-- OpenTI -->\n    <div class=\"os-card\" data-repo=\"DaRL-LibSignal\/OpenTI\">\n      <h3>Open-TI<\/h3>\n      <div class=\"os-meta\">LLM Agent \u00b7 IJMLC<\/div>\n      <p>Open Traffic Intelligence \u2014 an augmented-language-model agent\n         that turns natural-language instructions into traffic analysis,\n         simulator control, and signal-policy actions end-to-end.<\/p>\n      <div class=\"os-links\">\n        <a href=\"https:\/\/github.com\/DaRL-LibSignal\/OpenTI\" target=\"_blank\" rel=\"noopener\">\ud83d\udcbb Repo<\/a>\n        <a href=\"https:\/\/arxiv.org\/abs\/2401.00211\" target=\"_blank\" rel=\"noopener\">\ud83d\udcc4 Paper<\/a>\n      <\/div>\n      <div class=\"os-tags\"><span>LLM Agent<\/span><span>Traffic<\/span><span>Tool Use<\/span><\/div>\n    <\/div>\n\n  <\/div>\n<\/div>\n\n<script>\n(function () {\n  \/\/ Live GitHub metadata fetcher.\n  \/\/ For each .os-card[data-repo] on the page, fetches stars +\n  \/\/ pushed_at and renders them into the .os-meta line.\n  \/\/ Results are cached in localStorage for 6 hours.\n  var TTL_MS = 6 * 60 * 60 * 1000;\n\n  function cacheKey(owner, repo) {\n    return 'os_gh_' + owner.toLowerCase() + '\/' + repo.toLowerCase();\n  }\n  function readCache(owner, repo) {\n    try {\n      var raw = localStorage.getItem(cacheKey(owner, repo));\n      if (!raw) return null;\n      var p = JSON.parse(raw);\n      if (!p || typeof p.ts !== 'number') return null;\n      if ((Date.now() - p.ts) > TTL_MS) return null;\n      return p;\n    } catch (e) { return null; }\n  }\n  function writeCache(owner, repo, stars, pushed) {\n    try {\n      localStorage.setItem(cacheKey(owner, repo), JSON.stringify({\n        stars: stars, pushed: pushed, ts: Date.now()\n      }));\n    } catch (e) {}\n  }\n  function formatDate(iso) {\n    if (!iso) return '';\n    var d = new Date(iso);\n    if (isNaN(d.getTime())) return '';\n    return d.toLocaleDateString(undefined, { year:'numeric', month:'short', day:'numeric' });\n  }\n  function paint(card, stars, pushed) {\n    var meta = card.querySelector('.os-meta');\n    if (!meta) return;\n    var base = meta.getAttribute('data-base');\n    if (base === null) {\n      base = meta.textContent.trim();\n      meta.setAttribute('data-base', base);\n    }\n    var parts = [];\n    if (base) parts.push(base);\n    if (typeof stars === 'number') parts.push('\u2b50 ' + stars.toLocaleString());\n    var html = parts.join(' \u00b7 ');\n    if (pushed) html += ' <span class=\"gh-updated\">\u00b7 updated ' + formatDate(pushed) + '<\/span>';\n    meta.innerHTML = html;\n  }\n\n  function hydrate(card) {\n    var repo = card.getAttribute('data-repo');\n    if (!repo || repo.indexOf('\/') < 0) return;\n    var parts = repo.split('\/');\n    var owner = parts[0], name = parts[1];\n\n    var cached = readCache(owner, name);\n    if (cached) { paint(card, cached.stars, cached.pushed); return; }\n\n    fetch('https:\/\/api.github.com\/repos\/' + encodeURIComponent(owner) + '\/' + encodeURIComponent(name),\n          { headers: { 'Accept': 'application\/vnd.github+json' } })\n      .then(function (r) { if (!r.ok) throw 0; return r.json(); })\n      .then(function (d) {\n        var stars = (typeof d.stargazers_count === 'number') ? d.stargazers_count : null;\n        var pushed = d.pushed_at || null;\n        writeCache(owner, name, stars, pushed);\n        paint(card, stars, pushed);\n      })\n      .catch(function () { \/* silent \u2014 keep base meta *\/ });\n  }\n\n  function run() {\n    var cards = document.querySelectorAll('#os-section .os-card[data-repo]');\n    for (var i = 0; i < cards.length; i++) hydrate(cards[i]);\n  }\n  if (document.readyState === 'loading') {\n    document.addEventListener('DOMContentLoaded', run);\n  } else { run(); }\n})();\n<\/script>\n\n\n\n<h2 class=\"wp-block-heading has-text-align-center\"><strong>Sponsors<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-image aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"421\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-1024x421.jpg\" alt=\"\" class=\"wp-image-658\" srcset=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-1024x421.jpg 1024w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-300x123.jpg 300w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-768x316.jpg 768w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-1536x631.jpg 1536w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-2048x842.jpg 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignright size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"724\" height=\"350\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/ezgif.com-animated-gif-maker-2.gif\" alt=\"\" class=\"wp-image-666\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Generative AI<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Projects: <a href=\"https:\/\/github.com\/DaRL-LibSignal\/OpenTI\">OpenTI<\/a>, <a href=\"https:\/\/openreview.net\/forum?id=5GimteSrgW\">ICLR'26a<\/a>, <a href=\"https:\/\/darl-genai.github.io\/instructional_agents_homepage\/\">EACL'26a (Instructional Agents)<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2411.07559\">EACL'26b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2601.17329\">EACL'26c<\/a>, <a href=\"https:\/\/openreview.net\/forum?id=wXWfOThQCT\">ACL'25a<\/a>, <a href=\"https:\/\/openreview.net\/forum?id=g2CyeCHC32\">ACL'25b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2503.15850\">KDD'25a<\/a>, <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736963\">KDD'25b<\/a>, <a href=\"https:\/\/darl-genai.github.io\/heatwave\/\">IJCAI'25 (DeepShade)<\/a>, <a href=\"https:\/\/arxiv.org\/pdf\/2410.14368\">SDM'25a<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2403.04124\">SDM'25b<\/a>, <a href=\"https:\/\/darl-genai.github.io\/shadebench\/\">KDD'26a (ShadeBench)<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2605.19220\">ICML'26a<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2605.19228\">ICML'26b<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Generative AI expresses the possibility of human-like AI. We investigate its potential and pitfalls.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<figure class=\"wp-block-image alignright size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"240\" height=\"232\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2024\/10\/Dataset_over_update-ezgif.com-optimize.gif\" alt=\"\" class=\"wp-image-282\" style=\"width:256px;height:auto\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignfull size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"504\" height=\"810\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2024\/10\/sim2real-sim.png\" alt=\"\" class=\"wp-image-257\" srcset=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2024\/10\/sim2real-sim.png 504w, https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2024\/10\/sim2real-sim-187x300.png 187w\" sizes=\"auto, (max-width: 504px) 100vw, 504px\" \/><\/figure>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Sim-to-real Transfer<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Papers: <a href=\"https:\/\/arxiv.org\/abs\/2502.13187\">Survey<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2606.07017\">KDD'26b<\/a>, <a href=\"https:\/\/openreview.net\/pdf?id=yn9dzttHvT\">ICLR'26b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2512.12211\">AAAI'26<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2507.15174\">RLC'25<\/a>, <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3716550.3725161\">ICCPS'25a<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2308.14284\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'24a<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2312.11551.pdf\">AAAI'24b<\/a>, <a href=\"https:\/\/github.com\/DaRL-LibSignal\/SynTraC\">ITSC'24 (SynTrac)<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2307.12388\" target=\"_blank\" rel=\"noreferrer noopener\">CDC'23a<\/a>,<a href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=10260398\" target=\"_blank\" rel=\"noreferrer noopener\">CASE'23<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Training in simulation would fail to perform similarly in the real world. We investigate how to transfer from simulation to the real world.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignright size-full is-resized is-style-uds-figure\"><img loading=\"lazy\" decoding=\"async\" width=\"291\" height=\"128\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/learn2sim.gif\" alt=\"\" class=\"wp-image-61\" style=\"width:382px;height:auto\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Learning to Simulate<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Papers: <a href=\"https:\/\/darl-genai.github.io\/shadebench\/\">KDD'26a (ShadeBench)<\/a> <a href=\"https:\/\/arxiv.org\/abs\/2402.06127v1\">ECML-PKDD'24a<\/a>,\u00a0<a href=\"https:\/\/www.public.asu.edu\/~hwei27\/_\" target=\"_blank\" rel=\"noreferrer noopener\">PADS'23<\/a>,\u00a0<a href=\"https:\/\/www.aimspress.com\/article\/doi\/10.3934\/era.2023057\" target=\"_blank\" rel=\"noreferrer noopener\">ERA'23<\/a>,\u00a0<a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539236\" target=\"_blank\" rel=\"noreferrer noopener\">KDD'22<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2003.00613\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'21<\/a>,\u00a0<a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/9458853\" target=\"_blank\" rel=\"noreferrer noopener\">ICDE'21<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2103.11845\" target=\"_blank\" rel=\"noreferrer noopener\">ECML-PKDD'20<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Realistic simulators are a step closer towards policymaking for the real world. We investigate how to build realistic simulators from real-world data.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignright size-full is-resized is-style-plain\"><img loading=\"lazy\" decoding=\"async\" width=\"316\" height=\"145\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/simulator.gif\" alt=\"\" class=\"wp-image-65\" style=\"width:381px;height:auto\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Simulator\/Environment Building\/Datasets<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Project websites:\u00a0<a href=\"https:\/\/openreview.net\/forum?id=gdoz6pCvZ9#discussion\">Terminal Simulation<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2402.06127v1\">CityFlowER<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2209.08483\" target=\"_blank\" rel=\"noreferrer noopener\">Honor of Kings (\u738b\u8005\u8363\u8000)<\/a>,\u00a0<a href=\"https:\/\/darl-libsignal.github.io\/\" target=\"_blank\" rel=\"noreferrer noopener\">LibSignal<\/a>,\u00a0<a href=\"https:\/\/cityflow-project.github.io\/\" target=\"_blank\" rel=\"noreferrer noopener\">CityFlow<\/a>,\u00a0<a href=\"https:\/\/github.com\/prescriptive-analytics\/challenge-docs\" target=\"_blank\" rel=\"noreferrer noopener\">Epidemic<\/a>,\u00a0<a href=\"https:\/\/cdn.glitch.me\/7bd1d2a7-e3a6-405c-b77c-2eb06ac05402%2FGeoSim-camera-ready.pdf?v=1634241952716\" target=\"_blank\" rel=\"noreferrer noopener\">Product Allocator<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Simulators are the foundation of reinforcement learning. We built a bunch of simulators for various applications, including MOBA Games, transportation, epidemics, and product allocation.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignright size-full is-resized is-style-plain\"><img loading=\"lazy\" decoding=\"async\" width=\"332\" height=\"145\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/advrl.gif\" alt=\"\" class=\"wp-image-62\" style=\"width:378px;height:auto\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Trustworthy Deep Learning<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Papers:\u00a0<a href=\"https:\/\/arxiv.org\/pdf\/2604.08708\">ACL'26a<\/a>, <a href=\"https:\/\/arxiv.org\/pdf\/2604.08708\">ACL'26b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2601.05366\">ACL'26c<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2411.07559\">EACL'26b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2601.17329\">EACL'26c<\/a>, <a href=\"https:\/\/arxiv.org\/html\/2403.06013v1\">SIGKDD Explorations'25<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2502.17026\">COLM'25<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2503.15850\">KDD'25a<\/a>, <a href=\"https:\/\/openreview.net\/forum?id=xXlboMUy2L\">KDD'25c<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2505.02247\">ICML'25a<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2406.09262\">ICML'25b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2308.14284\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'24a<\/a>,\u00a0 <a href=\"https:\/\/www.public.asu.edu\/~hwei27\/projects.html\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'24c<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2309.06800\" target=\"_blank\" rel=\"noreferrer noopener\">ICDM'23<\/a>,\u00a0 <a href=\"https:\/\/arxiv.org\/abs\/2307.12388\" target=\"_blank\" rel=\"noreferrer noopener\">CDC'23a<\/a>, <a href=\"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3615034\" target=\"_blank\" rel=\"noreferrer noopener\">CIKM'23<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2307.07832\" target=\"_blank\" rel=\"noreferrer noopener\">KDD'23<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2304.10722\" target=\"_blank\" rel=\"noreferrer noopener\">IJCAI'23<\/a>, <a href=\"https:\/\/www.aimspress.com\/article\/doi\/10.3934\/era.2023115\" target=\"_blank\" rel=\"noreferrer noopener\">ERA'23<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2211.10871\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'23<\/a>,\u00a0<a href=\"https:\/\/www.aaai.org\/AAAI22Papers\/IAAI-00029-JenkinsP.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">IAAI'22<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2106.10411\" target=\"_blank\" rel=\"noreferrer noopener\">IJCAI'21a<\/a>,\u00a0<a href=\"https:\/\/www.ijcai.org\/proceedings\/2021\/0228.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">IJCAI'21b<\/a>,\u00a0<a href=\"https:\/\/www.usenix.org\/system\/files\/sec21-wu-xian.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">USENIX Security'21 (Adversarial Policies)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The project investigates different aspects of trustworthy deep learning, including robust modeling for deep learning models with physics, reinforcement learning with offline data, and adversarial policy training.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignright size-full is-resized is-style-plain\"><img loading=\"lazy\" decoding=\"async\" width=\"600\" height=\"263\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/presslight.gif\" alt=\"\" class=\"wp-image-64\" style=\"width:378px;height:auto\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Deep Reinforcement Learning<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Papers:&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/1904.08117\" target=\"_blank\" rel=\"noreferrer noopener\">Survey (Arxiv)<\/a>,&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3447556.3447565\" target=\"_blank\" rel=\"noreferrer noopener\">Survey(KDD Explorations)<\/a>,&nbsp; <a href=\"https:\/\/arxiv.org\/abs\/2308.14284\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'24a<\/a>,&nbsp; <a href=\"https:\/\/arxiv.org\/abs\/2307.12388\" target=\"_blank\" rel=\"noreferrer noopener\">CDC'23a<\/a>,&nbsp; <a href=\"https:\/\/arxiv.org\/abs\/2307.12388\" target=\"_blank\" rel=\"noreferrer noopener\">CDC'23b<\/a>,&nbsp; <a href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=10260398\" target=\"_blank\" rel=\"noreferrer noopener\">CASE'23<\/a>,&nbsp; <a href=\"https:\/\/arxiv.org\/abs\/2304.10722\" target=\"_blank\" rel=\"noreferrer noopener\">IJCAI'23<\/a>,&nbsp; <a href=\"https:\/\/arxiv.org\/abs\/2211.10871\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'23<\/a>,&nbsp;<a href=\"https:\/\/traffic-signal-control.github.io\/a-thousand-lights.html\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'20<\/a>,&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3292500.3330949\" target=\"_blank\" rel=\"noreferrer noopener\">KDD'19<\/a>,&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357384.3357902\" target=\"_blank\" rel=\"noreferrer noopener\">CIKM'19a<\/a>,&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/1905.04722\" target=\"_blank\" rel=\"noreferrer noopener\">CIKM'19b<\/a>,&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3220096\" target=\"_blank\" rel=\"noreferrer noopener\">KDD'18<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The project systematically investigates \"smart\" traffic light control systems using deep reinforcement learning and evaluate its effectiveness on both synthetic and real-world traffic data.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-930feb06 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image alignright size-full is-resized is-style-plain\"><img decoding=\"async\" src=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/demand-prediction-edited.png\" alt=\"\" class=\"wp-image-68\" style=\"width:377px;height:auto\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<h2 class=\"wp-block-heading\">Spatio-temporal Data Mining<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Papers:&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3716550.3722023\">ICCPS'25b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2402.06127v1\">ECML-PKDD'24b<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2309.06800\" target=\"_blank\" rel=\"noreferrer noopener\">ICDM'23<\/a>,&nbsp;<a href=\"https:\/\/www.aimspress.com\/article\/doi\/10.3934\/era.2023057\" target=\"_blank\" rel=\"noreferrer noopener\">ERA'23a,<\/a>&nbsp;<a href=\"https:\/\/www.aimspress.com\/article\/doi\/10.3934\/era.2023115\" target=\"_blank\" rel=\"noreferrer noopener\">ERA'23b<\/a>,&nbsp;<a href=\"https:\/\/github.com\/DerronXu\/TRRN\/blob\/main\/4093.XuD.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'21<\/a>,&nbsp;<a href=\"https:\/\/chacha-chen.github.io\/papers\/NeurIPS_2020.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">NeurIPS'20 Workshop<\/a>,&nbsp; <a href=\"https:\/\/arxiv.org\/abs\/1803.01254\" target=\"_blank\" rel=\"noreferrer noopener\">AAAI'19<\/a>,&nbsp; <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3355563\" target=\"_blank\" rel=\"noreferrer noopener\">TKDD'19<\/a>,&nbsp; <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3308558.3313704\" target=\"_blank\" rel=\"noreferrer noopener\">WWW'19<\/a>,&nbsp; <a href=\"https:\/\/dl.acm.org\/doi\/10.1007\/978-3-319-93040-4_46\" target=\"_blank\" rel=\"noreferrer noopener\">PAKDD'18<\/a>,&nbsp;<a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/2983323.2983667\" target=\"_blank\" rel=\"noreferrer noopener\">CIKM'16<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This project investigated the spatial-temporal prediction problems with applications in smart cities.<\/p>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p class=\"mb-2\">Open Source \/ Software Our group values practical and reproducible research. Below are open-source libraries, benchmarks, and tools built by the DaRL group and our collaborators, spanning reinforcement learning for transportation, large-model agents, and spatio-temporal data mining. For the full list of repositories, see our GitHub organization CityFlow Traffic Simulator \u00b7 WWW&#8217;19 A multi-agent reinforcement-learning&#8230;<\/p>\n","protected":false},"author":284,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"class_list":["post-57","page","type-page","status-publish","hentry"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Research - DaRL Group \/ Hua Wei<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/labs.engineering.asu.edu\/hw\/research\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Research - DaRL Group \/ Hua Wei\" \/>\n<meta property=\"og:description\" content=\"Open Source \/ Software Our group values practical and reproducible research. Below are open-source libraries, benchmarks, and tools built by the DaRL group and our collaborators, spanning reinforcement learning for transportation, large-model agents, and spatio-temporal data mining. For the full list of repositories, see our GitHub organization CityFlow Traffic Simulator \u00b7 WWW&#8217;19 A multi-agent reinforcement-learning...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/labs.engineering.asu.edu\/hw\/research\/\" \/>\n<meta property=\"og:site_name\" content=\"DaRL Group \/ Hua Wei\" \/>\n<meta property=\"article:modified_time\" content=\"2026-06-11T00:17:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-1024x421.jpg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@realhuawei\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/\",\"url\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/\",\"name\":\"Research - DaRL Group \\\/ Hua Wei\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2026\\\/03\\\/sponsors-1024x421.jpg\",\"datePublished\":\"2023-12-15T23:54:17+00:00\",\"dateModified\":\"2026-06-11T00:17:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/#primaryimage\",\"url\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2026\\\/03\\\/sponsors-scaled.jpg\",\"contentUrl\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2026\\\/03\\\/sponsors-scaled.jpg\",\"width\":2560,\"height\":1052},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/research\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/#website\",\"url\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/\",\"name\":\"Data Mining and Reinforcement Learning Group \\\/ Hua Wei\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/#organization\",\"name\":\"DaRL Group \\\/ Hua Wei\",\"url\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2023\\\/12\\\/logo-darl.png\",\"contentUrl\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2023\\\/12\\\/logo-darl.png\",\"width\":1024,\"height\":1024,\"caption\":\"DaRL Group \\\/ Hua Wei\"},\"image\":{\"@id\":\"https:\\\/\\\/labs.engineering.asu.edu\\\/hw\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/realhuawei\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Research - DaRL Group \/ Hua Wei","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/labs.engineering.asu.edu\/hw\/research\/","og_locale":"en_US","og_type":"article","og_title":"Research - DaRL Group \/ Hua Wei","og_description":"Open Source \/ Software Our group values practical and reproducible research. Below are open-source libraries, benchmarks, and tools built by the DaRL group and our collaborators, spanning reinforcement learning for transportation, large-model agents, and spatio-temporal data mining. For the full list of repositories, see our GitHub organization CityFlow Traffic Simulator \u00b7 WWW&#8217;19 A multi-agent reinforcement-learning...","og_url":"https:\/\/labs.engineering.asu.edu\/hw\/research\/","og_site_name":"DaRL Group \/ Hua Wei","article_modified_time":"2026-06-11T00:17:58+00:00","og_image":[{"url":"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-1024x421.jpg","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_site":"@realhuawei","twitter_misc":{"Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/labs.engineering.asu.edu\/hw\/research\/","url":"https:\/\/labs.engineering.asu.edu\/hw\/research\/","name":"Research - DaRL Group \/ Hua Wei","isPartOf":{"@id":"https:\/\/labs.engineering.asu.edu\/hw\/#website"},"primaryImageOfPage":{"@id":"https:\/\/labs.engineering.asu.edu\/hw\/research\/#primaryimage"},"image":{"@id":"https:\/\/labs.engineering.asu.edu\/hw\/research\/#primaryimage"},"thumbnailUrl":"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-1024x421.jpg","datePublished":"2023-12-15T23:54:17+00:00","dateModified":"2026-06-11T00:17:58+00:00","breadcrumb":{"@id":"https:\/\/labs.engineering.asu.edu\/hw\/research\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/labs.engineering.asu.edu\/hw\/research\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/labs.engineering.asu.edu\/hw\/research\/#primaryimage","url":"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-scaled.jpg","contentUrl":"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2026\/03\/sponsors-scaled.jpg","width":2560,"height":1052},{"@type":"BreadcrumbList","@id":"https:\/\/labs.engineering.asu.edu\/hw\/research\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/labs.engineering.asu.edu\/hw\/"},{"@type":"ListItem","position":2,"name":"Research"}]},{"@type":"WebSite","@id":"https:\/\/labs.engineering.asu.edu\/hw\/#website","url":"https:\/\/labs.engineering.asu.edu\/hw\/","name":"Data Mining and Reinforcement Learning Group \/ Hua Wei","description":"","publisher":{"@id":"https:\/\/labs.engineering.asu.edu\/hw\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/labs.engineering.asu.edu\/hw\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/labs.engineering.asu.edu\/hw\/#organization","name":"DaRL Group \/ Hua Wei","url":"https:\/\/labs.engineering.asu.edu\/hw\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/labs.engineering.asu.edu\/hw\/#\/schema\/logo\/image\/","url":"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/logo-darl.png","contentUrl":"https:\/\/labs.engineering.asu.edu\/hw\/wp-content\/uploads\/sites\/163\/2023\/12\/logo-darl.png","width":1024,"height":1024,"caption":"DaRL Group \/ Hua Wei"},"image":{"@id":"https:\/\/labs.engineering.asu.edu\/hw\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/realhuawei"]}]}},"_links":{"self":[{"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/pages\/57","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/users\/284"}],"replies":[{"embeddable":true,"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/comments?post=57"}],"version-history":[{"count":6,"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/pages\/57\/revisions"}],"predecessor-version":[{"id":801,"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/pages\/57\/revisions\/801"}],"wp:attachment":[{"href":"https:\/\/labs.engineering.asu.edu\/hw\/wp-json\/wp\/v2\/media?parent=57"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}