Sébastien Larivée


Sorted by New

Wiki Contributions


DeepMind: Generally capable agents emerge from open-ended play

This seems to support Reward is Enough


More specifically:

DM simulates a lower fidelity version of real world physics  -> Applies real world AI methods -> Achieves generalised AI performance. 

This is a pretty concrete demonstration that current AI methods are sufficient to achieve generality, just need more real world data to match the more complex physics of reality.