Human-level control through deep reinforcement learning

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.

[ Parent | on HN ]

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.

[ Parent | on HN ]