.png){kind=icon}
.png){kind=icon}
Return
Goals as reward-producing programs
.png){kind=icon}
PRE
AI
DOI：10.1038/s42256-025-00981-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
People are remarkably capable of generating their own goals, beginning with child's play and continuing into adulthood. Despite considerable empirical and computational work on goals and goal-oriented behaviour, models are still far from capturing the richness of everyday human goals. Here we bridge this gap by collecting a dataset of human-generated playful goals (in the form of scorable, single-player games), modelling them as reward-producing programs and generating novel human-like goals through program synthesis. Reward-producing programs capture the rich semantics of goals through symbolic operations that compose, add temporal constraints and allow program execution on behavioural traces to evaluate progress. To build a generative model of goals, we learn a fitness function over the infinite set of possible goal programs and sample novel goals with a quality-diversity algorithm. Human evaluators found that model-generated goals, when sampled from partitions of program space occupied by human examples, were indistinguishable from human-created games. We also discovered that our model's internal fitness scores predict games that are evaluated as more fun to play and more human-like.
Keywords:
REINFORCEMENT
MIND