This is the artifact of "MoGym: Using Formal Models for Training and Verifying Decision Agents" In this artifact we demonstrate how to use all functionalities of MoGym. We describe MoGym's Open AI Gym based API implemented in `Momba`. We start with having a formal model in `JANI` and describe how to learn a decision agent in form of a neural network (NN) resolving the non-determinism of one of the automata. Then we describe how to assess the quality of the learned NN with the help of the statistical model checker `modes`. In addition, we explain how to use the general interface of `modes` for resolving non-determinism during statistical model checking (SMC), which connects to an arbitrary decision agent over a socket communication. With this artifact it is possible to reproduce all experiments described in the submitted paper (Sect. 4) and even more.