Re:Deep Reinforcement Learning: Pong from Pixels
by karmapolice on Wednesday June 01, 2016 @06:21AM
(#11813309)
With further training I don't think it's possible: since those movements are not useful nor harmful, they will appear in winning and losing matches.
A possible solution might be including some distance traveled metric in the reward function...
[ Parent
| on HN ]
There are no comments on this comment yet.