Mastering Stratego
deepmind.com
Mastering Stratego
1–10 of 128 posts
Re: Mastering Stratego
#2Re: Mastering Stratego
#3Re: Mastering Stratego
#4I’m curious about the comparisons to poker. I know the hot algorithm in poker solvers is counter factual regret minimization. The article indicates that the feedback cycle is too long for those algorithms to work but I’d be curious to learn more about the relationship from CFR to what’s tried here, if any.
Re: Mastering Stratego
#5Can 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?
Stratego is 40% information, 40% strategy, maybe 10% tactics. If you know where is the flag it's trivial to win in almost all situations. Fighting into imperfect information is literally all the game.
Re: Mastering Stratego
#6Great article. I played Stratego a lot as a kid and it always felt simpler than chess, go , or poker so it’s surprising it’s a much bigger game tree unless you stop and think. I’m curious about the comparisons to poker. I know the hot algorithm in poker solvers is counter factual regret minimization. The article indicates that the feedback cycle is too long for those algorithms to work but I’d be curious to learn mor…
Re: Mastering Stratego
#7https://github.com/deepmind/open_spiel/tree/master/open_spie...
Re: Mastering Stratego
#8Can 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?
Dota is a pretty local game. 70% tactics, 20% strategy. Maybe 10% information. Yes you have warding game but for an AI with no cost of looking at heroes inventories (humans need to waste attention and move their map) AI already has huge advantage over humans in the imperfect information part. Usually fighting into the imperfect information is the bad choice. Stratego is 40% information, 40% strategy, maybe 10% tactic…
Like is it just the speed of your clicking? Or is it more than that, like the most basic kinds of strategic decisons?
Re: Mastering Stratego
#9Re: Mastering Stratego
#10Earlier quoted context omitted.
Dota is a pretty local game. 70% tactics, 20% strategy. Maybe 10% information. Yes you have warding game but for an AI with no cost of looking at heroes inventories (humans need to waste attention and move their map) AI already has huge advantage over humans in the imperfect information part. Usually fighting into the imperfect information is the bad choice. Stratego is 40% information, 40% strategy, maybe 10% tactic…
Is Tactics the same thing as execution? Like is it just the speed of your clicking? Or is it more than that, like the most basic kinds of strategic decisons?