[RL-baseline] Model v2, original action set, LR 1e-3

[ziritrion]

We learned that by modifying the learning rate from our original 1e-2 to 1e-3 we could improve the training dramatically.

With Learning Rate of 1e-2 (commit befd201), we could barely pass a Running Reward of 30, as the images below show:

By simply changing the learning rate to 1e-3 we managed to get a Running Reward right below 700 at some points, but noticed a dramatic drop near the 10k episode mark (commit 970f84a)

Here's an example run with the latest model. Notice that the Running Reward achieved by the model at the end of the 10k episodes is about 250 or so, so the behaviour isn't particularly good.
https://user-images.githubusercontent.com/1465235/111752396-f06b4a80-8895-11eb-97c5-4e0a29091cd1.mp4