News for hackers. Stuff that matters.

A comment on Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning. Parent comment

Re:Mastering the Game of Stratego with Model-Free Multiagent... by dr_orpheus on Monday July 11, 2022 @12:13PM (#32058069)
> A significant chunk of the game is just trying to remember which unit is which of the things you've seen so far

While this does get hard the further you go in the game, a think a more significant portion of the strategy is trying to predict newly moving units based on what is happening in the game. i.e. I just took a 7 unit with my 8. And now my opponent is coming straight towards me with a unit from elsewhere. Is it a 9 or 10, is it a bluff to drive me off, to drive me in to a spot where the actual 9 or 10 is waiting?

[ Parent | on HN ]
Re:Mastering the Game of Stratego with Model-Free Multiagent... by aidenn0 on Monday July 11, 2022 @12:49PM (#32058567)
Did they renumber the pieces? In the set I played as a kid a scout was 9 and a Marshall was 1...
[ Parent | on HN ]
Re:Mastering the Game of Stratego with Model-Free Multiagent... by wakamoleguy on Monday July 11, 2022 @01:19PM (#32058914)
Yes, around 2000 they swapped the numbers. Most recent versions treat the Spy as 1 and Marshal as 10. Classic versions ranked the Marshal as 1 and Scouts as 9, with the Spy designated as S.
[ Parent | on HN ]
Re:Mastering the Game of Stratego with Model-Free Multiagent... by andruby on Monday July 11, 2022 @03:01PM (#32060271)
I bought a set to play with my kids and felt like something was off but couldn’t really recall. Thanks!
[ Parent | on HN ]
Re:Mastering the Game of Stratego with Model-Free Multiagent... by spywaregorilla on Monday July 11, 2022 @01:21PM (#32058944)
Computers are better at such problems.
[ Parent | on HN ]