steffen/marl-factory-grid
1
0
Fork 0
mirror of https://github.com/illiumst/marl-factory-grid.git synced 2025-10-31 12:37:27 +01:00
Code Issues Packages Projects Releases Wiki Activity

added own dqn

Browse Source
This commit is contained in:
romue
2021-06-16 23:20:40 +02:00
parent 2432dca173
commit 26d7705e19
1 changed files with 0 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
algorithms/_base.py
View File

@@ -146,9 +146,6 @@ class BaseQlearner:
rewards = torch.tensor([e.reward for e in experience]).float()
dones = torch.tensor([e.done for e in experience]).float()
print(rewards)
next_q_values = self.target_q_net(next_obs).detach().max(-1)[0]
target_q_values = rewards + (1. - dones) * self.gamma * next_q_values