Re:Human-level control through deep reinforcement learning
by morenoh149 on Thursday February 26, 2015 @05:12AM
(#9111869)
I expect it could go far. Mind you I only did parts of Artificial Intellegence: A modern approach but the Q-learning algorthim seems very flexible. https://en.wikipedia.org/wiki/Q-learning
It basically keeps doing good stuff, while exploring to get out of local minimas.
[ Parent
| on HN ]
There are no comments on this comment yet.