Able is a community for developers to build and share their knowledge.

Already a member? Sign in

I like doing things.

In my last post, we introduced a function approximator to estimate the value function of each state. With this, we were able to subtract a s...

In my last post, I implemented REINFORCE which is a simple policy gradient algorithm. We saw that while the agent did learn, the high varian...

In my last post, I derived the policy gradient theorem which allows us to approximate a gradient that we can use to shift our policy in a di...

Welcome This is the first post in what will (hopefully) be a small series of blog posts documenting my understanding of various concepts and...