|
|
@@ -99,11 +99,12 @@ Now we should move to the agent program.
|
|
|
for example ROOMBA
|
|
|
|
|
|
__agent__
|
|
|
-||||||
|
|
|
+
|
|
|
+| | | | | |
|
|
|
|---|---|---|---|---|
|
|
|
-|||What the world look like|$\leftarrow$||
|
|
|
-|||$\downarrow$||environment
|
|
|
-|Action reuse|$\rightarrow$|What actually should i do|$\rightarrow$||
|
|
|
+|||What the world look like|$\leftarrow$|
|
|
|
+|||$\downarrow$|environment|
|
|
|
+|Action reuse|$\rightarrow$|What actually should i||| |do|$\rightarrow$|||
|
|
|
|
|
|
This model performs well when the environment is *fully observable*.
|
|
|
|
