Referring to deep learning as just being good for "perception" really strains credulity. Chess has historically been a prototypical exercise in reasoning, but since variables weren't involved in it's mastery, I guess it's perception now?https://twitter.com/GaryMarcus/status/1068897657530138629 …
-
I mean, you *could* define the whole of model-based reinforcement learning as (symbolic?) reasoning. But since your argument is that symbolic reasoning is neglected in DL, that would imply the field has been ignoring model-based RL, which it clearly hasn't.
i think you need operations over variables in your RL to build your models properly... (and my beef with RL is mainly w model-free stuff like DQN, not w RL in principle)