search

joaopauloschuler / neural-api

CAI NEURAL API - Pascal based deep learning neural network API optimized for AVX, AVX2 and AVX512 instruction sets plus OpenCL capable devices including AMD, Intel and NVIDIA.
GNU Lesser General Public License v2.1
371 stars 198 forks source link

Board game and Supervised learning #98

Open StepHaze opened 1 year ago

StepHaze commented 1 year ago

Hello! can I use your wonderful deep learning neural network library for my task: there's a board game (with sowing mechanism: Mancala, Oware, etc.) and I have thousands of games of top players (with moves and result). I would like to train a game neural network using Supervised learning. How is it possible? Please point me in the right direction.

joaopauloschuler commented 1 year ago

Hello @StepHaze , Applying NN for playing games is certainly possible. There are currently 234 papers at https://paperswithcode.com/task/atari-games about this subject.

I do not have any source code example with CAI solving this problem.

StepHaze commented 1 year ago

Thank you for your answer. I'm not sure that Atari games are what I need to implement a supervised learning for a game of perfect information.

joaopauloschuler commented 1 year ago

I would have a look at https://paperswithcode.com/task/game-of-chess

StepHaze commented 1 year ago

Thanks. It's all about reinforcement learning. I would like to use a supervised learning.