Skip to main content
Open Access Publications from the University of California

Creativity, Compositionality, and Common Sense in Human Goal Generation


Inspired by notions of intrinsic motivation (Schmidhuber, 2010) and play as proposing and solving arbitrary problems (Chu and Schulz, 2020b), we report initial progress toward computational modeling of playful goal generation. We create an embodied, 3D environment resembling a child's room, and ask study participants to play in the environment and then create a scorable game. We propose to model games using a domain-specific language, which represents each game as a computer program. These programs act as reward-generating functions, mapping states visited by an agent as they play a game to the score they should receive. We then analyze our corpus of program representations to highlight four key aspects of human games that would contribute to constructing effective computational models of game generation: creativity, compositionality, common sense, and context sensitivity.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View