全屏
載入
暫停
Tutorial
Agent 1:
Config
Blocks
Agent 2:
Config
Blocks
AI Reinforce Lab: Explore. Train. Compete.
選擇下列遊戲快速載入：
Multi-Armed Bandit
Dinosaur Jump
Taiko Beat
Easy Shoot
Maze2D
5
Q-Learning
print
repeat
times
do
repeat
times
do
0
+
▾
=
▾
item
▾
set
item
▾
to
if
do
print
0
2
4
6
0
2
4
Cumulative Reward Over Time
Time (s)
Cumulative Reward
plotly-logomark
0
2
4
6
−1
0
1
2
3
4
Q-table Heatmap (Two Actions)
State Dimension X
State Dimension Y
plotly-logomark
Export Q-table
5
Q-Learning
print
repeat
times
do
repeat
times
do
0
+
▾
=
▾
item
▾