Paper Repro: Deep Neuroevolution

In this post, D reproduce the recent Uber paper “Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning”, which amazingly showed that simple genetic algorithms sometimes performed better than apparently advanced reinforcement learning algorithms on well studied problems such as Atari games.

I reach state of the art (at the time) performance on Frostbite, a game that had stumped reinforcement learning algorithms for years before Uber finally solved it with this paper. I also learn about the dark art of training neural networks using genetic algorithms.

View full post here

In the event you would want to cite this blog post, you could use this template:

@electronic{ecoffet2018paper_repro_deep_neuroevolution,
  title={Paper Repro: Deep Neuroevolution},
  author={Ecoffet, Adrien},
  url = {https://medium.com/towards-data-science/paper-repro-deep-neuroevolution-756871e00a66},
  year={2018}
}