Z
Zhenhui Li
Researcher at Pennsylvania State University
Publications - 125
Citations - 8757
Zhenhui Li is an academic researcher from Pennsylvania State University. The author has contributed to research in topics: Reinforcement learning & Graph (abstract data type). The author has an hindex of 39, co-authored 120 publications receiving 5572 citations. Previous affiliations of Zhenhui Li include Salesforce.com & University of Illinois at Urbana–Champaign.
Papers
More filters
Book ChapterDOI
Targeted Knowledge Transfer for Learning Traffic Signal Plans
TL;DR: This paper proposes a batch learning framework where the targeted transfer reinforcement learning (TTRL-B) is introduced to speed up learning and is the first work to consider the impact of slow learning in RL on real-world applications.
Proceedings ArticleDOI
Searching online book documents and analyzing book citations
TL;DR: This work proposes a hybrid approach for extracting title and authors from a book that combines results from CiteSeer, a rule based extractor, and a SVM based Extractor, leveraging web knowledge and introduces an open-book search engine that extracts and indexes metadata, contents, and bibliography from online PDF book documents.
Proceedings ArticleDOI
Learning to Simulate Vehicle Trajectories from Demonstrations
TL;DR: This paper unprecedentedly treats the problem of traffic simulation as a learning problem, and proposes learning to simulate (L2S) vehicle trajectory using the generative adversarial imitation learning framework to estimate the policy that provides sequential decisions for the vehicle given real-world demonstrations.
Book ChapterDOI
Representation Learning for Large-Scale Dynamic Networks
TL;DR: A dynamic network embedding approach for large-scale networks that incrementally updates the embeddings by considering the changes of the network structures and is able to dynamically learn the embedding for networks with millions of nodes within a few seconds.
Journal ArticleDOI
Citywide Traffic Volume Inference with Surveillance Camera Records
TL;DR: A framework named CityVolInf is proposed to infer citywide traffic volume based on surveillance camera records using a semi-supervised learning-based similarity module with a novel simulation module to address the above challenges.