github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-09 06:58:11 -05:00
Code Issues Packages Projects Releases Wiki Activity

Fixed DDPG example (#667)

Browse Source
This commit is contained in:
jspieler
2023-03-09 20:49:52 +01:00
committed by GitHub
parent 022c5835fc
commit da7fb4b227
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/deep_deterministic_policy_gradient.py
View File

@@ -173,12 +173,12 @@ class DeepDeterministicPolicyGradient:
for param, target_param in zip(
optim.get_parameters(self.actor), optim.get_parameters(self.target_actor)
):
target_param.assign(param * tau + target_param * (1.0 - tau))
target_param.assign(param.detach() * tau + target_param * (1.0 - tau))
for param, target_param in zip(
optim.get_parameters(self.critic), optim.get_parameters(self.target_critic)
):
target_param.assign(param * tau + target_param * (1.0 - tau))
target_param.assign(param.detach() * tau + target_param * (1.0 - tau))
def choose_action(self, state: Tensor, evaluate: bool = False) -> NDArray:
mu = self.actor.forward(state, self.max_action)