Hacker News Reader

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.

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/

Reply on news.ycombinator.com