Whether an AI that plays StarCraft, DotA, or Overwatch succeeds or fails against top players, we'd have learned nothing from the outcome. Wins -- congrats, you've trained on enough data. Fails -- go back, train on 10x more games, add some bells & whistles to your setup, succeed.
-
-
If OpenAI Five beats professional players, it would be interesting to see if that is so because it learned some new "tricks" humans didn't discover before. Thus, it might help human players get even better.
-
Learning something about DotA that helps human players to improve is a likely outcome of OpenAI Five, but that is using AI to research on DotA, not viceversa.
End of conversation
New conversation -
-
-
How is this different from AlphaGO?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Do you know of any good benchmarks for generalization in machine learning algorithms?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Compensate the sparse training data with a physics or rule based model?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I do not agree, completely. This is not supervised learning, this is Reinforcement Learning, where the agents extrapolate a complex behavior from raw rewards coming from an environment. If this is pattern recognition, then humans are so.
-
We can model human intelligence as pattern recognition, but we are *extremely good* at it We need zero samples, a description (words) may be enough to create a pattern (BTW it is holistic/hierarchical), recognize it, and be disappointed (high entropy) by it, because WTF is this:pic.twitter.com/hUQu35h8ev
End of conversation
New conversation -
-
-
I may be biased, but IMHO StarCraft is a different beast due to fog of war, e.g. may choose to lose a unit to see something For the first time, actively seeking to update a theory of mind/strategy of the rival and adapting to it _might be necessary_ to defeat best human players
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.