Leveraging deep generative models for non-parametric distributions in reinforcement learning
This thesis explores the use of deep generative models to enhance distribution representations in reinforcement learning (RL), leading to improved exploration, stability, and performance. It focuses on two roles of distributions in RL: policy distributions and action distributions. For policy distri...
Main Author: | Tang, Shi Yuan |
---|---|
Other Authors: | Zhang Jie |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/173455 |
Similar Items
-
Leveraging deep learning for visual understanding of videos
by: Tan, Clement Xian Ren
Published: (2024) -
Representation discovery in non-parametric reinforcement learning
by: Zewdie, Dawit (Dawit Habtamu)
Published: (2014) -
Deep reinforcement learning for complex environment 1
by: Goh, Peng Aik
Published: (2024) -
Deep reinforcement learning for optimal resource allocation (II)
by: Uday, Nihal Arya
Published: (2024) -
Revolutionizing intrusion detection in industrial IoT with distributed learning and deep generative techniques
by: Hamouda, Djallel, et al.
Published: (2024)