Policy Gradient Methods¶
Loss modules for policy gradient algorithms.
|
A parent PPO loss class. |
|
Clipped PPO loss. |
|
KL Penalty PPO loss. |
|
TorchRL implementation of the A2C loss. |
|
Reinforce loss module. |
Loss modules for policy gradient algorithms.
|
A parent PPO loss class. |
|
Clipped PPO loss. |
|
KL Penalty PPO loss. |
|
TorchRL implementation of the A2C loss. |
|
Reinforce loss module. |