Gary Marcus

It’s question of emphasis, in part, but if I were running your ship I would spend more time exploring principled ways of building hybrids, and more kinds of of hybrids, and more time on on open-ended problems.

Other than Neural Turing Machines, AlphaGo, GraphNets, GQN, SPIRAL, etc? I'm sure you'd run things differently, but this is a far cry from the DRL centric narrative of the Wired article.

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.

your dichotomy is false. MCTS is core to RL, but it relies on symbolic computation. famous folk like @geoffreyhinton going around saying we don’t need symbol manipulation , but you can’t have MCTS if you give up symbol-manipulation. rhetoric and reality don’t line up.

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.