29 Papers
46 Citations
Minwoo Lee is an academic researcher from University of North Carolina at Charlotte. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 6, co-authored 29 publications. Previous affiliations of Minwoo Lee include Colorado State University & National Service of Learning.
Chat about Author
Papers
Faster reinforcement learning after pretraining deep networks to predict state dynamics
Charles W. Anderson,Minwoo Lee,Daniel L. Elliott +2 more
- 12 Jul 2015
TL;DR: It is demonstrated that learning a predictive model of state dynamics can result in a pretrained hidden layer structure that reduces the time needed to solve reinforcement learning problems.
•Posted Content
Few-Shot Keyword Spotting With Prototypical Networks
Archit Parnami,Minwoo Lee +1 more
TL;DR: This paper proposes a solution to the few-shot keyword spotting problem using temporal and dilated convolutions on prototypical networks and demonstrates keyword spotting of new keywords using just a small number of samples.
45
Delay-Optimal Traffic Engineering through Multi-agent Reinforcement Learning
Pinyarash Pinyoanuntapong,Minwoo Lee,Pu Wang +2 more
- 01 Apr 2019
TL;DR: A model-free TE framework is proposed that adopts multi-agent reinforcement learning for distributed control to minimize the E2E delay and results show that the combination of several extensions, such as double learning, expected policy evaluation, and on-policy learning, can provide superior E 2E delay performance under high traffic load cases.
36
STAR: Simultaneous Tracking and Recognition through Millimeter Waves and Deep Learning
Prabhu Janakaraj,Kalvik Jakkala,Arupjyoti Bhuyan,Zhi Sun,Pu Wang,Minwoo Lee +5 more
- 01 Sep 2019
TL;DR: A deep microdoppler learning system is proposed, which utilizes deep neural networks to automatically learn and extract the discriminative features in the mmWave gait biometic data to distinguish a large number of people from each other.
18
DEVS/HLA-Based Modeling and Simulation for Intelligent Transportation Systems
Jong-Keun Lee,Minwoo Lee,Sung-Do Chi +2 more
- 01 Aug 2003
TL;DR: The authors performed distributed homogeneous traffic simulation by extending an existing developed DEVS-based I3D2 transportation simulation system to an HLA-based distributed simulation environment, which gives an object-oriented and hierarchical modular modeling and simulation environment of traffic models that have complicated, dynamic features of the real world.
17