BriefGPT.xyz
Mar, 2022
关于实用的强化学习：可证明的鲁棒性、可扩展性和统计效率
On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency
HTML
PDF
Thanh Nguyen-Tang
TL;DR
本文旨在研究多种强化学习方法如鲁棒性RL，分布式RL 和离线RL，并为每个方法提供算法以及未来的相关研究方向。
Abstract
This thesis rigorously studies fundamental
reinforcement learning
(RL) methods in modern practical considerations, including
robust rl
,
distribut
→