Proximal Policy Optimization
E162136
UNEXPLORED
Proximal Policy Optimization is a popular reinforcement learning algorithm that improves policy gradient methods by using clipped objective functions to achieve stable and efficient training.
Aliases (1)
Referenced by (2)
| Subject (surface form when different) | Predicate |
|---|---|
|
John Schulman
("“Proximal Policy Optimization Algorithms”")
→
|
authorOf |
|
John Schulman
→
|
notableWork |