Keen Software House has improved their General artificial intelligence. It could already Pong, a Breakout Game and an Artificial Brain simulator and now it is able to work with delayed rewards and create a hierarchy of goals.
The AI was able to control movement through a maze like map and learn the rules of a game.
It used reinforcement learning to seek rewards and avoid punishment.
AI is able to follow a complex chain of strategy in order to complete its main goal. It can assign a hierarchical order to its various goals and plan ahead so it reaches an even bigger goal.
![]()
![]()
Read more »![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
The AI was able to control movement through a maze like map and learn the rules of a game.
It used reinforcement learning to seek rewards and avoid punishment.
AI is able to follow a complex chain of strategy in order to complete its main goal. It can assign a hierarchical order to its various goals and plan ahead so it reaches an even bigger goal.
Read more »
