mlpack
blog
|
Proximal Policy Optimization - Week 7
Proximal Policy Optimization - Week 7
This week, I focus on the the update()
function part, there are some other functionality need to implement.
Task
- Added actor model updating part.
- Implemented the PPO-Clip.
- Added synchronizing the oldActorNetwork.
- Cleaned up the redundant code.
Thanks for reading :).
Generated by 1.8.13