I'm Miguel González Duque, a mathematician from the Universidad Nacional de Colombia. I'm mostly interested in the intersection between probabilistic modeling and geometry.
I'm currently a PhD student at the Creative AI Lab at the IT University of Copenhagen, under the supervision of Prof. Sebastian Risi. We are developing systems that create and adapt game content to users. I have also started collaborating with Søren Hauberg's lab at DTU, working on generative modelling and differential geometry. I'm also currently doing a PhD Sabbatical at the Bosch Center for AI working with Leonel Rozo.
Feel free to contact me at miguelgondu(at)gmail(dot)com.
We train 2-dimensional VAEs on Mario and Zelda and define a graph in latent space only where playable levels live. This lets us sample and interpolate safely.
We used an NCA as the decoder of a Variational Autoencoder. (Main work done by Rasmus Berg Palm; I only played a secondary role.)
We induced geometries in latent space by pulling back the Fisher-Rao metric.
We applied a Bayesian Optimization approach to dynamically adjusting difficulty.
arxiv - publication - code
We used Gaussian Processes and Bayesian Optimization to find good levels for one bot using a prior from another bot.
arxiv - publication - code
We conditioned a StarCraft2 bot on strategies and optimized for the best strategy. This image was made by Niels Justesen.
arxiv - publication - code
My M.Sc. Thesis (Mathematics at UNAL-Med). During my first stay at ITU, I collaborated with Niels, Sebastian and Daniel Cabarcas on applying dimensionality reduction to strategies, and creating bots for StarCraft 2.