
Yoshua Bengio: equipping AI with higher level cognition and creativity
The Robot Brains Podcast
00:00
Aspects of Reward Shaped Compact Models in Reinforcement Learning
In reinforcement learning, reward shaping plays a very big role in the speed of learning. And so it seems like if you can learn a very well shaped compact model, whatever the counterpart would be outside of reinforcement learning, it could potentially allow the inference system to be learned much faster. Do you see a similar spectrum of possibilities? Yes.
Transcript
Play full episode