News for hackers. Stuff that matters.
Re:Using Keras and Deep Deterministic Policy Gradient to pla... by modeless on Tuesday October 11, 2016 @04:13PM (#12688113)
This is cool, but unlike some other recent neural game players [1] [2], it doesn't look at the screen at all. It also has an objective function which is tightly coupled to this game. Therefore this work is not easily generalizable to other video games, nor would it be useful for a real-world self-driving car.

[1] http://vizdoom.cs.put.edu.pl/ [2] https://deepmind.com/research/dqn/

Re:Using Keras and Deep Deterministic Policy Gradient to pla... by fchollet on Tuesday October 11, 2016 @04:18PM (#12688160)
It would be easy to replace the input features with representations from a pixel-level convnet, to make this is a "real" self-driving car, going from pixels to commands.

Anyone interested in this type of research: consider cloning the repo and implementing this modification, it would make a great starter project.

Re:Using Keras and Deep Deterministic Policy Gradient to pla... by yanpanlau on Tuesday October 11, 2016 @05:58PM (#12688861)
It is quite easy to change the input features as pixels and fit into convnet under Keras (That's why I love Keras so much). However, gym_torcs only support 64x64 pixels and it is hard to see by human eyes, IMHO.

https://github.com/ugo-nama-kun/gym_torcs/issues/4

Re:Using Keras and Deep Deterministic Policy Gradient to pla... by modeless on Tuesday October 11, 2016 @07:06PM (#12689245)
Interesting, yeah that seems a bit small. Would be a fun project to fix!