I stare at screens a lot. You probably do too. Staring at screens is easier with apps like f.lux and iris, which apply color filters to our displays to reduce the amount of blue light our eyes consume. If your screen has mostly white colors and you use f.lux, the...

In the last yarlp blog post, I ran Double Deep Q-Learning on Atari, which took around 1-1.5 days to train per Atari environment for 40M frames. I wanted to implemented something faster, namely A2C (Advantage Actor Critic). It’s related to A3C by Mnih et al, 2016, without the asynchronous part....

Reinforcement Learning…again? I wanted to re-create the latest Deep Q-Learning results on Atari, a huge milestone for AI Research in the past few years. Apart from the official code in Lua, I found several Python implementations on github, notably this one from OpenAI or this one among many others. Very...

There are a lot of RL packages out there, tensorforce, rllab, openai-lab, baselines, and the list goes on. It’s hard to know however, how any of those implementations stack up to published state-of-the-art results. There are several reasons, some are: The standard RL tasks (Mujoco & Atari) are extremely sensitive...

I’ve been wanting to go cross-country skiing since my dreams were shattered last winter in Stockholm (X-country ice-skating instead of skiing). So we made it happen in Montana at the Izaak Walton Inn. If you do want to visit Montana or Glacier National Park in the winter, I don’t think...

OS X 10.12.6 was working great for me…until I wanted to run tensorflow on GPU. OS X 10.13 didn’t help. Unfortunately tensorflow isn’t Mac friendly, because “As of version 1.2, TensorFlow no longer provides GPU support on Mac OS X.”. I don’t even understand what that means since you can...

After building a desktop a few months ago, I left it running on Linux. It wasn’t all that bad, as long as I didn’t need to use any applications with a real GUI 😂. This left me in a state of dismay, not using my new build as much as...

There are a lot of packages out there for deep Reinforcement Learning (RL), and so it became obvious to me that there needed to be yet another implementation! I’m calling it yarlp, Yet Another Reinforcement Learning Package! I’m developing it mostly for educational purposes. Here are several great implementations that...