Hello World

First post. More to come.

Here’s some math to make sure KaTeX works:

\[\nabla_\theta J(\theta) = \mathbb{E}_{\pi_\theta} \left[ \nabla_\theta \log \pi_\theta(a|s) \cdot A^{\pi_\theta}(s, a) \right]\]

That’s the policy gradient theorem. If you can read it, the blog is working.