Train on Small, Play the Large: Scaling Up Board Games with

Playing board games is considered a major challenge for both humans and AI researchers. Because some complicated board games are quite hard to learn, humans usually begin with playing on smaller boards and incrementally advance to master larger board strategies. Most neural network frameworks that are currently tasked with playing board games neither perform such incremental learning nor possess capabilities to automatically scale up. In this work, we look at the board as a graph and combine a graph neural network architecture inside the AlphaZero framework, along with some other innovative improvements. Our ScalableAlphaZero is capable of learning to play incrementally on small boards, and advancing to play on large ones. Our model can be trained quickly to play different challenging board games on multiple board sizes, without using any domain knowledge. We demonstrate the effectiveness of ScalableAlphaZero and show, for example, that by training it for only three days on small Othello boards, it can defeat the AlphaZero model on a large board, which was trained to play the large board for 30 days.

Best Strategy Board Games for 2023 - CNET

How China's high-speed rail network got built so fast

New York MTA's 20-Year Plan: Grand Central Overhaul, Flood Guards - Bloomberg

Choosing the Right GPU for LLM Inference and Training

Fisher-Price® Thomas & Friends Wooden Railway Thomas Engine by Fisher Price

PDF) Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

Best board games 2023: must-haves for your collection

Reinforcement learning: From board games to protein design

PDF) Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

Rolling Line on Steam

PDF] Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

How to Use Gameplay to Enhance Classroom Learning