Skip to content

Instantly share code, notes, and snippets.

@JKCooper2
Created May 3, 2016 08:15
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save JKCooper2/5bda9ccb530ea35c9947ce84093fdb42 to your computer and use it in GitHub Desktop.
Save JKCooper2/5bda9ccb530ea35c9947ce84093fdb42 to your computer and use it in GitHub Desktop.
Unachievable score resulting from action returning 20 rather than 2
Environment currently sets: velocity += (action-1)*0.001 + math.cos(3*position)*(-0.0025) without a bound checks on the input
Will look at adding range check to the environment
@wojzaremba
Copy link

Good catch. We will constrain it.

This env suppose to examine ability of exploration.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment