5 datasets found

The corridor environment is a simple environment where the agent has to determine whether the rewarding cell (colored yellow) is at the top or bottom, based on the color of the...

The Reconnaissance Blind TicTacToe (RBT) dataset is a variation of the Reconnaissance Blind Chess (RBC) challenge. It is a game of TicTacToe where the agent cannot see the moves...

A POAPS program for iterative improvement on descriptions for images

A POAPS program for labeling that manages uncertainty without exposing it to the user

A programming language with a POMDP inside