Game-AI Forum

Hi, I wrote a CUDA kernel for convolution, and it outperforms cuDNN for small tensors. cuDNN is efficient for large batches, but slow for small batches. Here are some numbers for my Go program. This is a network with 80 layers of 128 channels, 19x19 board, V100 (PCIExpress), half-precision, NHWC ten...

Hi, Here is a short report about my Crazy Zero experiments. Crazy Zero is a generic implementation of AlphaZero. I already used it for Go, shogi, gomoku, renju, othello, and chess. The version that played on the Ataxx server (http://server.ataxx.org/) is less than one day old. The network architectu...

https://www.deepmind.com/blog/article/AlphaStar-Grandmaster-level-in-StarCraft-II-using-multi-agent-reinforcement-learning Direct link to the paper: https://storage.googleapis.com/deepmind-media/research/alphastar/AlphaStar_unformatted.pdf The most interesting contribution seems to be their league s...

Microsoft has produced a very strong AI:
https://medium.com/syncedreview/meet-mi ... b0a63eb871
Very little technical details, unfortunately.

https://icga.org/?page_id=2984

Thanks Jonathan for accepting to become the new President of the ICGA!

Ataxx has a community of AI programmers, with a few open-source engines

• Wikipedia: https://en.wikipedia.org/wiki/Ataxx
• Ataxx AI community: https://www.ataxx.org/

https://ludii.games/

A great collection of games and their rules by our Maastricht friends.

Hi,

The TORCS forum might be a better place to ask:
http://www.berniw.org/trb/forum/threadlist.php

Rémi

I probably won't attend. But it does look like a very nice event.

https://project.dke.maastrichtuniversity.nl/cig2018/ Computer games offer not only a killer application for computational intelligence (CI), machine learning and search, but also provide a compelling domain in which problem solving and decision making meet artifact creation, to provide highly immers...