wassname/DeepRL
1
0
Fork 0
mirror of https://github.com/wassname/DeepRL.git synced 2026-09-10 11:40:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improve normalizer for scalar

Browse Source
This commit is contained in:
Shangtong Zhang
2017-10-07 21:23:02 -06:00
parent fae9a85f31
commit 51f125c01e
3 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
async_worker/continuous_actor_critic.py
+1 -1
View File
@@ -48,7 +48,7 @@ class ContinuousAdvantageActorCritic:
steps += 1
total_reward += reward
reward = np.asscalar(self.reward_normalizer(np.array([reward])))
reward = self.reward_normalizer(reward)
if deterministic:
if terminal:
async_worker/ppo.py
+1 -1
View File
@@ -79,7 +79,7 @@ class ProximalPolicyOptimization:
batched_steps += 1
episode_length += 1
reward = np.asscalar(self.reward_normalizer(np.array([reward])))
reward = self.reward_normalizer(reward)
rewards.append(reward)
if done: