Alert button
Picture for Jieping Ye

Jieping Ye

Alert button

Stochastic Gradient Descent without Full Data Shuffle

Jun 12, 2022
Lijie Xu, Shuang Qiu, Binhang Yuan, Jiawei Jiang, Cedric Renggli, Shaoduo Gan, Kaan Kara, Guoliang Li, Ji Liu, Wentao Wu, Jieping Ye, Ce Zhang

Figure 1 for Stochastic Gradient Descent without Full Data Shuffle
Figure 2 for Stochastic Gradient Descent without Full Data Shuffle
Figure 3 for Stochastic Gradient Descent without Full Data Shuffle
Figure 4 for Stochastic Gradient Descent without Full Data Shuffle
Viaarxiv icon

Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms

Feb 22, 2022
Shikai Luo, Ying Yang, Chengchun Shi, Fang Yao, Jieping Ye, Hongtu Zhu

Figure 1 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Figure 2 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Figure 3 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Figure 4 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Viaarxiv icon

Rethinking Graph Convolutional Networks in Knowledge Graph Completion

Feb 08, 2022
Zhanqiu Zhang, Jie Wang, Jieping Ye, Feng Wu

Figure 1 for Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Figure 2 for Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Figure 3 for Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Figure 4 for Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Viaarxiv icon

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Oct 19, 2021
Shuang Qiu, Jieping Ye, Zhaoran Wang, Zhuoran Yang

Viaarxiv icon

A Deep Value-network Based Approach for Multi-Driver Order Dispatching

Jun 08, 2021
Xiaocheng Tang, Zhiwei Qin, Fan Zhang, Zhaodong Wang, Zhe Xu, Yintai Ma, Hongtu Zhu, Jieping Ye

Figure 1 for A Deep Value-network Based Approach for Multi-Driver Order Dispatching
Figure 2 for A Deep Value-network Based Approach for Multi-Driver Order Dispatching
Figure 3 for A Deep Value-network Based Approach for Multi-Driver Order Dispatching
Figure 4 for A Deep Value-network Based Approach for Multi-Driver Order Dispatching
Viaarxiv icon

Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms

Jun 04, 2021
Xiaocheng Tang, Fan Zhang, Zhiwei Qin, Yansheng Wang, Dingyuan Shi, Bingchen Song, Yongxin Tong, Hongtu Zhu, Jieping Ye

Figure 1 for Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
Figure 2 for Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
Figure 3 for Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
Figure 4 for Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
Viaarxiv icon

Reinforcement Learning for Ridesharing: A Survey

May 03, 2021
Zhiwei Qin, Hongtu Zhu, Jieping Ye

Figure 1 for Reinforcement Learning for Ridesharing: A Survey
Viaarxiv icon

Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning

Mar 08, 2021
Yan Jiao, Xiaocheng Tang, Zhiwei Qin, Shuaiji Li, Fan Zhang, Hongtu Zhu, Jieping Ye

Figure 1 for Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
Figure 2 for Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
Figure 3 for Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
Figure 4 for Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
Viaarxiv icon

Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

Dec 07, 2020
Bingyu Liu, Yuhong Guo, Jieping Ye, Weihong Deng

Figure 1 for Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Figure 2 for Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Figure 3 for Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Figure 4 for Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Viaarxiv icon