Finding Friend and Foe in Multi-Agent Games

Re:Finding Friend and Foe in Multi-Agent Games by chadmeister on Saturday June 08, 2019 @04:17AM (#20131269)

I think you are exactly right. The algo is simply outmemorizing it's human counterparts. This isn't a very good paper at all.

[ Parent | on HN ]

Re:Finding Friend and Foe in Multi-Agent Games by Detry322 on Monday June 10, 2019 @11:48AM (#20147822)

I don't think this is true. On ProAvalon, human players can see the full history of the game at all times [1], and use it to make decisions. DeepRole, on the other hand, can only use its internal belief state. This belief state is only a summary of what has happened in the game - DeepRole has no way of knowing who went on previous missions, or how people voted, or who proposed what. See above for more detail.

[1] See this video for an example: https://www.youtube.com/watch?v=LKdY4Us0Ci4

[ Parent | on HN ]