4 datasets found

We study the problem of making item recommendations to ephemeral groups, which comprise users who purchase very few (or no) items together.

The dataset is used for multitask representation learning in linear MDPs. It contains 80 different tasks, each with a different destination position, fire configuration, and...

The Sprites dataset has 672 synthetically rendered animated characters (sprites). The dataset is split into a training set with 500, a validation set with 72, and a test set...

The dataset used in this paper is a reinforcement learning dataset, specifically the SimpleQuestion dataset, which contains questions answerable using Wikidata as the knowledge...