typo notes

Author: vpj

docs/rl/dqn/index.html

@@ -302,4 +302,4 @@ <h3>Double <span ><span class="katex"><span aria-hidden="true" class="katex-html
     handleImages()
 </script>
 </body>
-</html>
+</html>

docs/sitemap.xml

@@ -554,7 +554,7 @@
 
     <url>
       <loc>https://nn.labml.ai/diffusion/stable_diffusion/latent_diffusion.html</loc>
-      <lastmod>2022-09-15T16:30:00+00:00</lastmod>
+      <lastmod>2022-12-21T16:30:00+00:00</lastmod>
       <priority>1.00</priority>
     </url>
 
@@ -1177,7 +1177,7 @@
 
     <url>
       <loc>https://nn.labml.ai/transformers/mha.html</loc>
-      <lastmod>2022-09-07T16:30:00+00:00</lastmod>
+      <lastmod>2022-12-24T16:30:00+00:00</lastmod>
       <priority>1.00</priority>
     </url>
 

labml_nn/rl/dqn/__init__.py

@@ -51,7 +51,7 @@ class QFuncLoss(Module):
     ### Target network 🎯
     In order to improve stability we use experience replay that randomly sample
     from previous experience $U(D)$. We also use a Q network
-    with a separate set of paramters $\textcolor{orange}{\theta_i^{-}}$ to calculate the target.
+    with a separate set of parameters $\textcolor{orange}{\theta_i^{-}}$ to calculate the target.
     $\textcolor{orange}{\theta_i^{-}}$ is updated periodically.
     This is according to paper
     [Human Level Control Through Deep Reinforcement Learning](https://deepmind.com/research/dqn/).