News for hackers. Stuff that matters.

A comment on AlphaGo Beats Lee Sedol in Final Game. Parent comment

Re:AlphaGo Beats Lee Sedol in Final Game by aquadrop on Tuesday March 15, 2016 @06:06AM (#11288576)
It's still based on human games. It plays itself but the way it plays was inherited from human. I wonder if there is some fundamental barrier to what you can reach with reinforcement depending on your base.
[ Parent | on HN ]
Re:AlphaGo Beats Lee Sedol in Final Game by aflinik on Tuesday March 15, 2016 @10:57AM (#11290076)
Having it learn on human games was just a way of speeding up the initialization process before running reinforcement learning, it didn't limit the state tree that was being searched later on.
[ Parent | on HN ]
Re:AlphaGo Beats Lee Sedol in Final Game by relic on Tuesday March 15, 2016 @07:24AM (#11288809)
It is based on human games until it can explore well enough to sufficiently break away from local optimums.
[ Parent | on HN ]