Currently there are several theories for how neural activity may represent probability distributions.

In practice, however, recursive updating often leads to poor trade-off solutions across tasks because approximate inference is necessary for most models of interest.

It is often convenient to model high-dimensional datasets as probability distributions.

We will often use variational optimization. When the variational family is not made explicit it means that the optimization is over all functions with the correct domain and codomain, e.g.

Determinantal point processes (DPPs) are popular probabilistic models of diversity.

Finally, we benchmark five tabular agents in our newly proposed benchmark.