Skip to content

Commit

Permalink
fixing typo in polic iteration
Browse files Browse the repository at this point in the history
  • Loading branch information
WKaiZ committed Oct 14, 2024
1 parent 12b64aa commit 10dcb98
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion mdp/policies-iteration.md
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ $$\begin{aligned}
&= {\operatorname{argmax}}\{slow: 2,\:\: fast: 3\} \\
&= \boxed{fast}\\
\pi_{1}(warm) &= {\operatorname{argmax}}\{slow: 0.5 \cdot [1 + 0.5 \cdot 2] + 0.5 \cdot [1 + 0.5 \cdot 2] ,\:\: fast: 1 \cdot [-10 + 0.5 \cdot 0]\} \\
&= {\operatorname{argmax}}\{slow: 3,\:\: fast: -10\} \\
&= {\operatorname{argmax}}\{slow: 2,\:\: fast: -10\} \\
&= \boxed{slow}
\end{aligned}$$

Expand Down

0 comments on commit 10dcb98

Please sign in to comment.