On this page videos are shown which give an overview of the experiments done with the
Offline MOMDP model to play hide-and-seek; the robot is the seeker and the person is the hider.
Both players do one discrete step at the same, such that the time is discrete.
Triangle Reward
In these experiments the Triangle reward is used to play hide-and-seek.
Simple Reward
In these experiments the Simple reward (a reward of 1 if winning and -1 when losing) is used to play hide-and-seek.
Follow us!