Zak Jost

I'm reference the code [here](https://github.com/openai/InfoGAN/blob/master/infogan/algos/infogan_trainer.py#L73-L76). The mutual information calculation is `disc_mi_est = disc_ent - disc_cross_ent`. If you reference `disc_ent`, it is the negative mean of `disc_log_q_c`, where `disc_log_q_c = self.model.reg_disc_latent_dist.logli_prior(disc_reg_z)`....

Create example for Ant Colony Optimization

1

I'm creating an issue to track this line of work. One quick question: I am using the latest commit in Mesa to develop (i.e., using `SolaraViz` instead of `JupyterViz`)--is this...