Image-to-Image Regression for GO territory classification

I’m trying to implement a neural network that is able to generate an image indicating territory occupation given a board state for GO (a strategy board game). Input images are 19x19x1 grayscale images, with white pixels indicating white pieces, black pixels indicating black pieces, and gray pixels indicating unoccupied areas. Output images are 19x19x1 grayscale…

Image-to-Image Regression for GO territory classification

I’m trying to implement a neural network that is able to generate an image indicating territory occupation given a board state for GO (a strategy board game). Input images are 19x19x1 grayscale images, with white pixels indicating white pieces, black pixels indicating black pieces, and gray pixels indicating unoccupied areas. Output images are 19x19x1 grayscale…

RL for two-player, hidden-information game

I am working towards using RL to create an AI for a two-player, hidden-information, turn-based board game. I have just finished David Silver’s RL course and dennybritz’s coding exercises, and so am relatively familiar with MC control, SARSA, Q-learning etc. However, the course was focused on single-player, perfect-information games, and I haven’t managed to find…