You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

gwern comments on A toy model of the control problem - Less Wrong Discussion

19 Post author: Stuart_Armstrong 16 September 2015 02:59PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (24)

You are viewing a single comment's thread.

Comment author: gwern 03 February 2016 08:06:25PM *  4 points [-]

Me and feep have implemented a slightly-tweaked version of this using a DQN agent in Reinforce.js. (Tabular turns out to be a bit infeasible.)

At the moment, if you want to modify settings like in Karpathy's demos, you'll have to do something like download it locally to edit, with a command like wget --mirror 'www.gwern.net/docs/rl/armstrong-controlproblem/index.html' && firefox ./www.gwern.net/docs/rl/armstrong-controlproblem/index.html

Comment author: Stuart_Armstrong 08 February 2016 10:59:32AM 0 points [-]

Thanks, most excellent!