An Empirical Investigation of Early Stopping Optimizations in Proximal Policy Optimization

An Empirical Investigation of Early Stopping Optimizations in Proximal Policy Optimization

Code-level optimizations, which are low-level optimization techniques used in the implementation of algorithms, have generally been considered as tangential and often do not appear in published pseudo-code of Reinforcement Learning (RL) algorithms. However, recent studies suggest these optimizations...

Full description

Bibliographic Details
Main Authors: Rousslan Fernand Julien Dossa, Shengyi Huang, Santiago Ontanon, Takashi Matsubara
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Artificial Intelligence
deep learning
reinforcement learning
proximal policy optimization
robotics and automation
robot learning
Online Access:https://ieeexplore.ieee.org/document/9520424/

Internet

https://ieeexplore.ieee.org/document/9520424/

Similar Items