bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
johnjim0816
2021-09-27 03:44:29 +08:00
parent 1e60b688fc
commit fb2affb69e
18 changed files with 191 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
codes/PPO/memory.py
View File

@@ -5,7 +5,7 @@ Author: John
Email: johnjim0816@gmail.com
Date: 2021-03-23 15:30:46
LastEditor: John
LastEditTime: 2021-03-23 15:30:55
LastEditTime: 2021-09-26 22:00:07
Discription:
Environment:
'''
@@ -24,14 +24,9 @@ class PPOMemory:
indices = np.arange(len(self.states), dtype=np.int64)
np.random.shuffle(indices)
batches = [indices[i:i+self.batch_size] for i in batch_step]
return np.array(self.states),\
np.array(self.actions),\
np.array(self.probs),\
np.array(self.vals),\
np.array(self.rewards),\
np.array(self.dones),\
batches
return np.array(self.states),np.array(self.actions),np.array(self.probs),\
np.array(self.vals),np.array(self.rewards),np.array(self.dones),batches
def push(self, state, action, probs, vals, reward, done):
self.states.append(state)
self.actions.append(action)