Noam Brown
speaker
1,199 appearances
1 recordings
1 series
first heard Dec 2022
last heard Dec 2022
Noam Brown’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
Well, whenever we play a game, we had a bot watching it to make sure that it wouldn't go off the rails and start threatening somebody or something like that.
That was, yeah, there were definitely like things that the bot would, would do that were not in line with like how humans would approach the game.
And that in a good way, the humans actually, you know, we we've talked to some expert diplomacy players about these results and their takeaways that, well, maybe humans are approaching this the wrong way.
And this is actually like the right way to play the game.
Well, I think...
You're asking kind of two questions there.
So one, modeling the irrationality and the suboptimality of humans.
In diplomacy, you can't treat all the other players like they're machines.
And if you do that, you're going to end up playing really poorly.
And so we actually ran this experiment.
So we trained a bot in a two-player zero-sum version of diplomacy, the same way that you might approach a game like chess or poker.
And the bot was superhuman.
It would crush any competitor.
And then we took that same training approach and we trained a bot for the full seven player version of the game through self-play without any human data.
And we stuck it in a game with six humans and it got destroyed.
Even in the version of the game where there's no explicit natural language communication, it still got destroyed because it just wouldn't be able to understand how the other players were approaching the game and be able to work with that.
Well, it would, for example, expect the human to support it in a certain way when the human would simply think like, no, I'm not supposed to support you here.
It's kind of like if you develop a self-driving car and it's trained completely from scratch with other self-driving cars, it might learn to drive on the left side of the road.
That's a totally reasonable thing to do if you're with these other self-driving cars that are also driving on the left side of the road.
But if you put it in an American city, it's going to crash.
Showing 941–960 of 1,199 · page 48 of 60
← Previous
Next →