Leveraging deep generative models for non-parametric distributions in reinforcement learning

• Main Author: Tang, Shi Yuan
• Other Authors: Zhang Jie
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science
• Online Access: https://hdl.handle.net/10356/173455
• Institution: Nanyang Technological University

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...