About
Contact & Profiles
A5044163254
Research Areas
- Multimodal Machine Learning Applications
- Reinforcement Learning in Robotics
- Advancements in Semiconductor Devices and Circuit Design
- Human Pose and Action Recognition
- Advanced Image and Video Retrieval Techniques
- Advanced Bandit Algorithms Research
- Visual Attention and Saliency Detection
- Domain Adaptation and Few-Shot Learning
University of Electronic Science and Technology of China
2022-2023
University of Copenhagen
2023
10.1007/s11063-022-10796-8
article
EN
Neural Processing Letters
2022-03-23
Recent success stories in reinforcement learning have demonstrated that leveraging structural properties of the underlying environment is key devising viable methods capable solving complex tasks. We study off-policy discounted learning, where some equivalence relation exists. introduce a new model-free algorithm, called QL-ES (Q-learning with structure), which variant (asynchronous) Q-learning tailored to exploit structure MDP. report non-asymptotic PAC-type sample complexity bound for...
10.3390/e25040584
article
EN
cc-by
Entropy
2023-03-29
10.1007/s11063-023-11190-8
article
EN
Neural Processing Letters
2023-03-09
Coming Soon ...