What happened to mastering StarCraft? Why did these guys give up after a mid tier pro player defeated the bot handily on live stream? They were super enthusiastic up until that point.
Mastering Stratego
101–110 of 128 posts
Re: Mastering Stratego
#102Earlier quoted context omitted.
FWIW one of the big things poker AI taught humans is massive overbets (eg. going all in for $200 over a $15 pot). This is scary to do well in practice, because the mathematically optimal bluff frequency approaches 50% as you increase the overbet size.
Is that heads-up only? Early massive overbets are nearly a coin toss in heads-up, so you break even in on a call and win on a fold, which is an equilibrium. However at a large table, you are going to get called only by the person who thinks they have the best hand, which is a lot better than the average hand of a typical opponent.
This is mostly done at the river where you've ended heads-up even when starting the hand with 6-10 players
Re: Mastering Stratego
#103On a related note and surely interesting to the HN crowd I invented Clesto which is similar to Stratego but a bit more like chess, based on an old chinese game: https://clesto.com/ - it is more quick to play and has open information.
Re: Mastering Stratego
#104Call me a cynic but the fact that after almost 10 years of AI hype we are still working our way down the list of popular board games is a bit of a downer for me. I mean, having AIs to play Stratego, Risk, Go, Diplomacy and what have you against sure is nice. But there are literally billions of dollars spent on these projects and I really come to the point where I just don't believe anymore that the current AI approac…
Alternative theory.
The actual models work fantastically well.
The board games are merely a cover to advertise to AI Researchers and portray AI as "innocent" in the public eye.
Stratego is Google goofing off.
The Ferrari AI models are being used by Google to absolutely swindle money in some ad tech niche.
Re: Mastering Stratego
#105I'd love to see them tackle Chess https://en.wikipedia.org/wiki/Proof_game
Re: Mastering Stratego
#106Earlier quoted context omitted.
> The problem here is that it's missing the "glue" to more real world applications. This is where more humdrum software engineering comes in. This is a bold statement. The world does not function based on "well-defined rewards". The concept of "common sense", which some consider table stakes for a human operating competently in our world, is mostly made up of things which are neither well-defined, nor allow a tremend…
> The world does not function based on "well-defined rewards". Humans can be neatly reduced to a "procreate, and make sure your progeny procreate" value function. A lot of apparent counterexamples to that turn out to make sense when 2nd order effects on progeny are considered.
Humans are adaptation-executors, not fitness-maximizers. Evolution has a procreation value function; humans have procreation-favoring traits.
Re: Mastering Stratego
#107Earlier quoted context omitted.
How many people study Stratego as much as an International Master studies chess?
I think there are probably very much diminishing returns. A small scene is probably pretty damn good at the top. Having hundreds of thousands of competitive players helps, but even with a small sample you are probably likely to get at least some very, very strong players. It's hard to think of a relevant real world example, but a fun corollary I'm familiar with is Fedex (Federico Perez Ponsa). He is a full chess Gran…
And the top 5 AoE2 players are significantly better than the top 20 who are significantly better than the top 100.
Re: Mastering Stratego
#108Earlier quoted context omitted.
FWIW one of the big things poker AI taught humans is massive overbets (eg. going all in for $200 over a $15 pot). This is scary to do well in practice, because the mathematically optimal bluff frequency approaches 50% as you increase the overbet size.
Is that heads-up only? Early massive overbets are nearly a coin toss in heads-up, so you break even in on a call and win on a fold, which is an equilibrium. However at a large table, you are going to get called only by the person who thinks they have the best hand, which is a lot better than the average hand of a typical opponent.
Its more common in heads up, yes.
In multiplayer you see it where ranges are narrowed, like 3bet pots or on turn/river
It matters less than you'd think because overbets imply you have a polarized range (nuts or air). You generally pick the bluffs to be hands that have cards blocking the best calling hand combinations.
Re: Mastering Stratego
#109Can anyone shed light on in what way this is more challenging than the starcraft or dota agents, which also had to work with imperfect information?
Great question! I would say the main reason why this work is significant is that StarCraft agent was bootstrapped from human replays, and Dota agent did not have game-theoretic guarantees on minimizing exploitability (i.e. how far the strategy is from Nash equilibrium). The R-NaD algorithm with neural nets (behind Stratego) starts from scratch, and has game-theoretic guarantees.
In principle, the AlphaStar's league approach (from StarCraft) could be done also in Stratego, and it would be very interesting to compare the two approaches. Note that AlphaStar is more expensive: it required to train N competing agents with pair-wise evaluation costing N^2, while Stratego's NeuRD trains a single agent.
Re: Mastering Stratego
#110Earlier quoted context omitted.
Yeah this is one of the reasons why I find it more dull than chess. There is an incentive to just not move your pieces, so that the other player thinks they're bombs. As a result, players only activate 2-3 pieces at a time. In chess, on the other hand, you are constantly moving your pawns to the other side to promotion, or otherwise trying to activate/coordinate all of your pieces for an attack. It makes me think tha…
> It makes me think that if deepmind for Stratego was trained to not lose instead of win, then the top strategy might be shuffling pieces and letting the enemy come to attack. No human would ever have the patience to play that way though. Tournament Stratego uses a clock, which reduces some of the issue there. It's not hard to beat a player that does what you suggest; just send some middling pieces after each piece t…
> It's not hard to beat a player that does what you suggest; just send some middling pieces after each piece that moves. You'll take the weak pieces and reveal the strong pieces.
But taking a strong piece means revealing a stronger piece of you own. That’s why I think the best strategy is to put almost all your weak pieces up front.,and wait for your enemy to reveal their pieces. Scouts, especially, are canon fodder that you sacrifice to find out information about the enemy and that you need to get rid of so that you get room to maneuver.