boredom

Interest & curiosity

Interestingness is the first derivative of the beauty $B$:

$$\text{interest}(X,O(t))=\frac{\partial B(X,O(t))}{\partial t}$$

… the extent to which data $X$ will improve the compressor (world model) for observer $O$.

Curiosity is the drive to improve the compressor:

$$\text{curiosity}=B(X,O(t))-B(X,O(t-1))$$

Link to original

Known beauty is boring.

Boredom

Boredom is implmented to stop exploration if for any $\mathcal{X}$, $E\le \eta$.
$\eta$ can be dynamically adjusted to fit an environment.

Link to original

What is boredom, besides being a tunable parameter?

A more complete version of the theory would let us derive a useful or even optimal value for boredom if given a learning problem or environment. We cannot do this. It is the next problem we will work on, and it is important. Does this mean you are hypothesizing that boredom is actively tuned? Yes we are predicting that. But can animals tune boredom? Geana and Daw showed this in a series of experiments. They reported that altering the expectations of future learning in turn alters self-reports of boredom. Others have shown how boredom and self-control interact to drive exploration.

Link to original