I have an open question about Prioritized Experience Replay from [Schaul15]. From my experiments, it seems that an equation in the publication is wrong, but maybe I’m overlooking something. I’d appreciate input.
To introduce ourselves to reinforcement learning with Deep-Q Networks (DQN), we’ll visit a standard OpenAI Gym problem, CartPole. We’ll cover deeper RL theory in a later post, but let’s get our hands dirty first, to build some intuition!
Kicking off a series of posts on OpenAI’s gym environment, I’ll cover some light bootstrapping to get us up and running more quickly. I promise, it will be short and sweet! I’ll be referring back to this from later posts in the series.
The complete series can be found on the bottom of this post and the latest version of the GitHub repo can be found here.
I’ve been awfully quiet recently, so let me catch you up on recent events.
Something that trips me up occasionally in C# is syntactic sugar with properties. Specifically, the difference between the fat arrow (
=>) and assignment (
=) with properties. Here’s a quick note to help clear up any confusion.
I just wrapped up another semester in Georgia Tech’s OMSCS program. This puts me 50% of the way to my Master’s degree in Computer Science, with another solid A grade in Human Computer Interaction!
I’ll be starting the summer semester in about another week, this time tackling Education Technology. Education and knowledge sharing have been passions of mine all my life – I’m really looking forward to this course!
Here’s a quick demo of a showcase set of Elm animations. Check out the GitHub repo under the
Showcase directory; run the app from the top-level
I’ve been meaning to publish a full-featured post for a while, but I’ve gotten bogged down in my studies once again. In the interest of not letting this content get too stale, I’m simply publishing what I have.
This expands upon the prior work I’ve blogged about, with some modifications. At the time of this writing, it demonstrates how to wire up two separate components, each with a collection of different animations (some of which are keyed off of one another, or off of other actions). The two components transition back and forth, too.
- The first component is an animated username/password form.
- The second component is an animated list of items.
At this point, pretty much all work starts from the
MinimalModules.elm file included in the repo and builds up from there. Just follow the comments and you should be able to hit the ground running, without worrying about the underlying piping.
I’ll likely expand this showcase set as I find time, but I won’t be updating this post.