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 …
-
Not at all, I'm quite the fan of MCTS, but it isn't a variable. The convolutions were a key bit of prior knowledge, but also weren't variables. You claimed that symbolic manipulation would be required to move past perception, but I fail to see any symbolic representations here.
-
-
MCTS is a search procedure, whereas you seem to be mistaking it for tree-structured representations. That they both have "tree" in the name seems besides the point.
-
the procedure operates over variables, with lots of variable binding taking place. that’s what matters. (and as it happens at least in the original Nature paper parts of the tree itself were encoded, if i recall correctly.)
- 5 more replies
New conversation -
-
-
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)
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.