Facebook taught an AI the ‘theory of mind’
Recent results in competitive games have shown that AI systems can outplay humans by far. But when it comes to real life, we need AI to work with us not against us.
As such a research team from Facebook taught an AI how to play the cooperative card game Hanabi (the Japanese word for fireworks), to gain a better understanding of how humans think.
The team particularly taught the system the theory of mind:
“Theory of mind is this idea of understanding the beliefs and intentions of other agents or other players or humans,” Noam Brown, a researcher at Facebook AI, told Engadget. “It’s something that humans developed from a very early age. But one AIs have struggled with for a very long time.”
“It’s trying to put itself in the shoes of the other players and ask why are they taking these actions, “and being able to infer something about the state of the world that it can’t directly observe,” added Brown.
Hanabi is game created by Antoine Bauza a French game designer. Hanabi charges its two to five players to construct five, 5-card stacks. Each stack is color coded and must be ordered numerically from one to five. The goal is to complete all the stacks or get as close to 25 points (five points per stack/five stacks) as possible once the team has run out of moves.
The interesting part about Hanabi is that the players do not know what is in their hands. They have to hold the cards looking away from them in such a way rivals will see what he or she I holding. The game is driven by sharing information between players.
Source: https://www.engadget.com/2019/12/06/facebook-taught-an-ai-the-theory-of-mind/
seangametheory 