Search

Your search keyword '"Liu, Yuchen"' showing total 87 results
Start Over Author "Liu, Yuchen" Publisher ieee
87 results on '"Liu, Yuchen"'

24. Scalable Model-based Policy Optimization for Decentralized Networked Systems

Author

Du, Yali, Ma, Chengdong, Liu, Yuchen, Lin, Runji, Dong, Hao, Wang, Jun, and Yang, Yaodong

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Optimization and Control (math.OC), Computer Science - Artificial Intelligence, Statistics - Machine Learning, FOS: Mathematics, Machine Learning (stat.ML), Computer Science - Multiagent Systems, Mathematics - Optimization and Control, Machine Learning (cs.LG), Multiagent Systems (cs.MA)
Abstract

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts. To alleviate the bias of model-generated data, we restrain the model usage for generating myopic rollouts, thus reducing the compounding error of model generation. To pertain the independence of policy update, we introduce extended value function and theoretically prove that the resulting policy gradient is a close approximation to true policy gradients. We evaluate our algorithm on several benchmarks for intelligent transportation systems, which are connected autonomous vehicle control tasks (Flow and CACC) and adaptive traffic signal control (ATSC). Empirically results show that our method achieves superior data efficiency and matches the performance of model-free methods using true models., 8 pages, 7 figures, accepted by The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

Published
2022

25. Class-Discriminative CNN Compression

Author

Liu, Yuchen, Wentzlaff, David, and Kung, S. Y.

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Compressing convolutional neural networks (CNNs) by pruning and distillation has received ever-increasing focus in the community. In particular, designing a class-discrimination based approach would be desired as it fits seamlessly with the CNNs training objective. In this paper, we propose class-discriminative compression (CDC), which injects class discrimination in both pruning and distillation to facilitate the CNNs training goal. We first study the effectiveness of a group of discriminant functions for channel pruning, where we include well-known single-variate binary-class statistics like Student's T-Test in our study via an intuitive generalization. We then propose a novel layer-adaptive hierarchical pruning approach, where we use a coarse class discrimination scheme for early layers and a fine one for later layers. This method naturally accords with the fact that CNNs process coarse semantics in the early layers and extract fine concepts at the later. Moreover, we leverage discriminant component analysis (DCA) to distill knowledge of intermediate representations in a subspace with rich discriminative information, which enhances hidden layers' linear separability and classification accuracy of the student. Combining pruning and distillation, CDC is evaluated on CIFAR and ILSVRC 2012, where we consistently outperform the state-of-the-art results.

Published
2022

43. Assimilation of Doppler Weather Radar Data with a Regional WRF-3DVAR System: Influence of Data Assimilation Volume on Precipitation Forecast

Author

Yu Fuliang, Wang Wei, Chuanzhe Li, Liu Yuchen, and Jia Liu

Subjects
Global Forecast System, Meteorology, Doppler radar, Weather forecasting, Atmospheric model, computer.software_genre, law.invention, Data assimilation, law, Weather Research and Forecasting Model, Quantitative precipitation forecast, Environmental science, Weather radar, computer
Abstract

In this study, the Weather Research & Forecast (WRF) model is adopted to provide mesoscale rainfall forecasts of four typical 24h duration rainstorms in North China and the DWR (Doppler Weather Radar) data is assimilated through the three-dimensional variational system (3DVar) in a cycling run mode to update the initial conditions of the WRF model. Global Telecommunication System (GTS) data produced by the National Center for Atmospheric Research (NCAR) are also assimilated as a benchmark. Before starting the assimilation process, the model spins up for 30h with the initial condition provided by the Global Forecast System. In the 1h WRF-3DVAR assimilation cycle, which means the DWR data are assimilated with a time interval of 1 h, the forecasts from the previous assimilation run serve as the background for the next run. A total of 24 runs in a cycle are performed for each 24h rainstorm. In order to highlight the contribution of the data assimilation volume, a 6h WRF-3DV AR assimilation cycle is also employed, which means, the DWR data are also assimilated with a time interval of 6 h. The results show that DWR data assimilation has improved the skill of high-intensity rainfall forecasts from the WRF model. The assimilation effect on the WRF model is not entirely decided by the amount of the assimilated data, but is closely related to the data quality.

Published
2021

49. Hybrid Nonlinear and Machine Learning Methods for Analyzing Factors Influencing the Performance of Large-Scale Transport Infrastructure.

Author

Song, Yongze, Wu, Peng, Li, Qindong, Liu, Yuchen, and Karunaratne, Lalinda

Abstract

Strategic maintenance is essential for sustainable road infrastructure development. Accurate estimation of road maintenance effects can support the assessment of maintenance strategies and reasonable allocation of budgets and resources. Road deterioration is affected by sophisticated factors, but accurate investigation of the integrated deterioration factors is limited. This study developed a dynamic trade-off model (DTOM), a hybrid nonlinear and machine learning method, for quantifying temporally varied impacts of factors and examining maintenance effects at the network level. Pavement deterioration factors are classified into three categories: (i) historical observations of roughness, (ii) pavement age, and (iii) traffic, climate and environment factors. Their respective impacts on pavements are estimated using a non-linear least square regression, a joinpoint regression and a random forest model, respectively. Vehicle-based laser scanner monitored high-resolution deterioration data was collected for a large spatial scale road network in Western Australia from 2007 to 2018. Results show that the resurfacing and rehabilitation are essential for strategic reduction of deterioration. Twelve-year maintenance activities reduced the distress of roughness by 7.5% and increased road performance (the percentage of roads with roughness lower than 2.085 IRI) by 14.5% for the whole road network. The DTOM has great potentials in accurately assessing infrastructure maintenance effects and predicting deterioration scenarios. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results