We combine our PolicyValueNetwork and MCTS implementations in alphagozero_agent.py. This module implements AlphaGoZeroAgent, which is the main AlphaGo Zero that conducts MCTS search and inference using PolicyValueNetwork to play games.
Combining PolicyValueNetwork and MCTS
Get Python Reinforcement Learning Projects now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
