Re:Human-level control through deep reinforcement learning
by ya3r on Thursday February 26, 2015 @05:04AM
(#9111844)
The amazing part of what DeepMind has achieved is its capability to learn from raw pixel input with deep convolutional neural networks, which as I understand it quite different from what you do.
Still the reinforcement learning part is the same, but reinforcement learning was not the main contribution of this nature paper.
Re:Human-level control through deep reinforcement learning
by craftit on Thursday February 26, 2015 @05:28AM
(#9111901)
Its not all that different, we take multiple asynchronous streams of messages integrate them into a coherent predictive model, and use that to feed the reinforcement learning. The messages can contain images, a simple case can be seen in the demo with a 1d vision sensor.
https://aiseedo.com/demos/cookiemonster/