For a noobie, why is this better than Deep RL or any of deep learning, or even needed at all? Just the limitations of scalable oversight and general problems with deep learning?
Is this the main thing thats proposed as a potential alternative to deep learning by agent foundations researchers??
For a noobie, why is this better than Deep RL or any of deep learning, or even needed at all? Just the limitations of scalable oversight and general problems with deep learning?
Is this the main thing thats proposed as a potential alternative to deep learning by agent foundations researchers??