visibility
Environment Render
show_chart
Training Performance
grid_on
Policy \(\pi(a|s)\)
Velocity (\(\dot{\theta}\))
+2.0
0.0
-2.0
-0.4
0.0
+0.4
Angle (\(\theta\))
Left
Right
monitoring
Value Function \(V(s)\)
Velocity (\(\dot{\theta}\))
+2.0
0.0
-2.0
-0.4
0.0
+0.4
Angle (\(\theta\))
Low
High
tune
Visualization Controls
X-axis
Y-axis