Commit 1b8690f5 authored by Eduard Pizur's avatar Eduard Pizur
Browse files

removed comments

parent c58dde4b
......@@ -139,7 +139,7 @@ dmypy.json
cython_debug/
### VisualStudioCode ###
.vscode/*
.vscode/
!.vscode/settings.json
!.vscode/tasks.json
!.vscode/launch.json
......
......@@ -94,19 +94,10 @@ class Agent():
q_vals_net = self.network.forward(states)
q_vals_next_target_net = self.target_network.forward(next_states)
# q_vals_net =
q_vals_net = q_vals_net.gather(1, actions.unsqueeze(-1)).squeeze(-1)
q_vals_next_target_net = q_vals_next_target_net.max(1)[0]
q_vals_next_target_net[dones] = 0.0
print(q_vals_net.gather(1, actions))
print(q_vals_net.gather(1, actions.unsqueeze(-1)).squeeze(-1))
# print(T.gather(q_vals_net,0,actions))
print(actions)
import sys
sys.exit(0)
q_target = rewards + DISCOUNT_FACTOR * q_vals_next_target_net
# optimize network
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment