Weirui Ye
Tsinghua University
13 Papers
Weirui Ye is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 2, co-authored 2 publications.
Chat about Author
Papers
Transferable Attention for Domain Adaptation
Ximei Wang,Liang Li,Weirui Ye,Mingsheng Long,Jianmin Wang +4 more
- 17 Jul 2019
TL;DR: This work presents Transferable Attention for Domain Adaptation (TADA), focusing the authors' adaptation model on transferable regions or images, and implements two types of complementary transferable attention: transferable local attention generated by multiple region-level domain discriminators to highlighttransferable regions, and transferable global Attention generated by single image-leveldomain discriminator to highlight transferable images.
402
Planning for Sample Efficient Imitation Learning
Zhao-Heng Yin,Weirui Ye,Qifeng Chen +2 more
- 18 Oct 2022
TL;DR: EI is proposed, a planning-based imitation learning method that can achieve high in-environment sample efficiency and performance simultaneously and shows over 4x gain in performance in the limited sample setting on state-based and image-based tasks and can solve challenging problems like Humanoid.
8
Proceedings Article
SpeedyZero: Mastering Atari with Limited Data and Time
TL;DR: SpeedyZero is developed, a distributed RL system built upon a state-of-the-art model-based RL method, EfficientZero, with a dedicated system design for fast distributed computation and two novel algorithmic techniques, Priority Refresh and Clipped LARS, to stabilize training with massively parallelization and large batch size.
3
Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions
Weirui Ye,Pieter Abbeel +1 more
- 23 Oct 2022
TL;DR: Experiments show that the Virtual MCTS (V-MCTS) can achieve comparable performances to the original search algorithm while requiring less than 50% search time on average, and it is believed that this approach is a viable alternative for tasks under limited time and resources.
Real-time scheduling of renewable power systems through planning-based reinforcement learning
Shaowei Liu,Jinbo Liu,Weirui Ye,Nan Yang,Guanglu Zhang,Haiwang Zhong,Chongqing Kang,Qirong Jiang,Xu Ri Song,Fang Chun Di,Yang Gao +10 more
TL;DR: In this paper , the authors proposed a systematic solution based on the state-of-the-art reinforcement learning algorithm and the real power grid environment, which enables planning and finer time resolution adjustments of power generators, including unit commitment and economic dispatch, thus increasing the grid's ability to admit more renewable energy.
1