Search found 6 matches

by Alvaro
Fri Jun 19, 2020 9:07 pm
Forum: MCTS, RL, and neural networks
Topic: AlphaZero approach for card games
Replies: 1
Views: 2421

AlphaZero approach for card games

Hi, A friend of mine is trying to develop a bot to play rummy, and he asked me for advice. I told him the trendy way of doing this for any game these days is to set up a neural network and train it from self-playing games. The obvious problem with adapting the AlphaZero approach to a game with lots ...
by Alvaro
Thu Dec 13, 2018 7:51 pm
Forum: General Discussion
Topic: Suggestions for games that use NPCs powered by a new type of AI that replicates creativity
Replies: 2
Views: 3031

Re: Suggestions for games that use NPCs powered by a new type of AI that replicates creativity

I'm curious to know what you have discovered in the months since the first post. I suspect that Psychology won't have anything illuminating to bring to the table. DeepMind's Alpha Zero's playing style is often described as creative, but I think that's just a descriptive label we assign, and not some...
by Alvaro
Mon Jun 19, 2017 3:17 pm
Forum: General Discussion
Topic: Welcome to Download the computer-go-dataset (1,645,958 SGFs)
Replies: 3
Views: 5218

Re: Welcome to Download the computer-go-dataset (1,645,958 SGFs)

These seem to be games between humans. Why is it called the "computer-go-dataset"?
by Alvaro
Fri Jan 29, 2016 10:43 am
Forum: General Discussion
Topic: AlphaGo
Replies: 4
Views: 8265

AlphaGo

In case you live under a rock, a couple of days ago the good guys at Google DeepMind published a deeply mind-boggling paper on Nature about their computer go player, AlphaGo. https://storage.googleapis.com/deepmind-data/assets/papers/deepmind-mastering-go.pdf It involves a few innovative ideas, but ...
by Alvaro
Fri Jan 01, 2016 11:47 am
Forum: General Discussion
Topic: Neural networks for Spanish checkers and beyond
Replies: 4
Views: 7732

Neural networks for Spanish checkers and beyond

I know that for three decades we have had to put up with people learning a little bit about neural networks and thinking they could solve every problem, when the reality is that they rarely solved any problems. But please don't run! :) It turns out there is this thing call "Deep Learning", which as ...