In response to a recent Coding Horror piece on Spartan programming I’d like to humbly submit two examples from my own recent work. First, in C++ we have: for (int i = 0; i < nstates; i++) { for (int a = 0; a < nactions; a++) { Q[i][a] += alpha * delta * e[i][a]; [...]
We’ve had some interesting discussion recently on the future goals of reinforcement learning. Penetration into industry seems to be a hot topic within the community, with the consensus being that reinforcement learning is currently too difficult to apply to problems without expertise. A related issue is that RL has no standard tookit, unlike machine learning, [...]
A New Approach to Manipulator control: The Cerebellar Model Articulation Controller by J.S Albus (1975) It is an old but good paper on a novel perceptron architecture that is widely used for reinforcement learning these days. I’ve created a bare-bones implementation in Python for those who are interested. You’ll need numpy and matplotlib. Here’s a [...]
It turns out that optimizing warehouse tasks is hard.
As I near completion on my final project for a course on reinforcement learning, I came across the following from Sutton’s page on tile coding: With the code described so far, there is a small probability that unrelated inputs will hash into some of the same tiles. In a group of tilings, usually there will [...]