Saying step back is definitely overly harsh. As OpenAI notes in their blog posts, this game is partially observable, continuous, non markovian, multi agent... it's hugely impressive they could scale up RL to deal with that and not reasonable to compare it to Atari.
You can’t just give OpenAI a mulligan on vision, if you want to claim superhuman performance. Not saying there is zero progess here but on the question of inducing a game from experience, and beating humans on a level playing field, it’s a step back compared to DQN on Atari.https://twitter.com/Smerity/status/1031248288958177280 …
-
-
-
Yes, this part is reasonable, and a good characterization of what the advance is. But the notion that a system that can sidestep all the vision and knowledge issues and still be labeled superhuman is silly. It may have won the game, but it wasn’t a fair fight.
- 1 more reply
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.