Tomohiro Nagasaka
Deep learning / Motion capture / Math强化学习基础
Published on January 31, 2021
D4PG
解说从强化学习的理论基础到D4PG之类的比较新的做法。
Q learning (Q学习)
https://zh.wikipedia.org/wiki/Q%E5%AD%A6%E4%B9%A0
Deep Q learning (深度Q-学习)
Actor, Clitic
DDPG
T3D
- target policy smoothing
- clipped double-Q learning
D4PG
If you like it, share it!