mlpack
blog
|
Proximal Policy Optimization - Week 3
Proximal Policy Optimization - Week 3
This week, the Prioritized Experience Replay pull request is merged. I have more time devoted to the Proximal Policy Optimization pull request.
Task
- Added forward and backward function for the surrogate loss.
- Added skeleton for ppo algorithm
- fixed the unclosed namespace problem
Thanks for reading :)
Generated by 1.8.13