Gary Marcus

Oh, so now AlphaGo is a hybrid? :) but yes I like a lot of that work and have advocated for some of it over time. I totally agree that DRL is not the only emphasis at DM; it’s just the largest (from what I can tell) and my least favorite and most visible, wrapped in one.

It's what you'd consider a hybrid. To RL folks the jump from DQN to MCTS doesn't change fields, so "hybrid" sounds weird.

Its not weird, it’s what (in conjunction) with RL makes it work. You have drunk the KoolAid if you ignore this.

MCTS is literally in RL 101 textbooks. The tree structure of MDPs is inherent in their temporal structure and core to RL. I'm sure it reminds you of Chomsky, parse trees, grammars, and that's fine, but not invoking them isn't "drinking the KoolAid", it's understanding the field.

Assimiling DQN and MCS + DRL as if they are same, without talking about why different design choices were made is misleading.

That's never happened. They are different algorithms in the same field (Seriously, look at RL textbooks). As my previous quote showed, they were quite up front with the different design choices.

And yet @sir_deenicus and I had to remind that you Alpha* even was a hybrid model...

Please reread the thread. I was explaining that *you* thought of them that way, and that was odd given *your* argument re DRL. Come on Gary, I'm trying to tweet in good faith, try to look for the intended interpretation.