Both can be & are true. Really telling to me is that DRL on its own worked for Atari games but not Go— and that DM’s spin on Go really downplayed the hybrid aspect that was essential to its success. (It was also apparently necessary to build in the rules for Go, unlike Atari.)
-
If MCTS is symbol manipulation, then so is the whole of RL. In which case, you've already won b/c we're doing RL. Using different definitions from the rest of the field isn't terribly fruitful though.
why don’t you ask Geoff what he means, or refer to my lengthy not for twitter discussion in algebraic mind
-
-
He's never been into RL, so I'm not sure how his opinions on a different topic are relevant here. Why don't you ask Sutton, Silver, or literally any other RL Prof whether or not "symbolic" is a useful distinction in their field.
-
DQNs are not symbolic for sure. Basically it is the distinction between model-free and model-based approaches.
- 1 more reply
New conversation -
-
-
And I've got your book, any section in particular address there symbolic nature of MCTS/RL?
-
no my directly. but chapters 2 and 3 explain why being clear about symbol-manipulation is important, and what is and is not important about this distinction. i would rather not continue this discussion in sound bite way, when the distinctions are subtle.
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.