A-TD3: An Adaptive Asynchronous Twin Delayed Deep Deterministic for Continuous Action Spaces

A-TD3: An Adaptive Asynchronous Twin Delayed Deep Deterministic for Continuous Action Spaces

Twin delayed deep deterministic (TD3) policy gradient is an effective algorithm for continuous action spaces. However, it cannot efficiently explore the spatial space and suffers from slow convergence, which is mainly due to the serial mode strategy in learning policies. On the other hand, asynchron...

Full description

Bibliographic Details
Main Authors: Jiaolv Wu, Q. M. Jonathan Wu, Shuyue Chen, Farhad Pourpanah, Detian Huang
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Reinforcement learning
asynchronous update
adaptive weight
continuous action spaces
Online Access:https://ieeexplore.ieee.org/document/9969602/

Internet

https://ieeexplore.ieee.org/document/9969602/

Similar Items