News for hackers. Stuff that matters.

A comment on Alpha Go Zero: How and Why It Works. Parent comment

Re:Alpha Go Zero: How and Why It Works by Barrin92 on Saturday November 04, 2017 @10:03PM (#15627824)
the OP is referring to the use of a GAN, which is a different type of setup.

GAN's were not used for alphaGo, as the article points out Deepmind uses reinforcement learning and MCTS.

[ Parent | on HN ]
Re:Alpha Go Zero: How and Why It Works by nschucher on Sunday November 05, 2017 @12:57AM (#15628220)
They're most likely referring to adversarial attacks where degenerate inputs are constructed that could cause AlphaGo Zero to perform sub-optimally or catastrophically fail (see OpenAI Research [0]). This is distinct from generative adversarial networks (GANs) or adversarial self-play (which I guess AlphaGo Zero is an example of).

[0] https://blog.openai.com/adversarial-example-research/

[ Parent | on HN ]