The second component of our AlphaGo Zero agent is the MCTS algorithm. In our mcts.py module, we implement an MCTreeSearchNode class, which represents each node in an MCTS tree during a search. This is then used by the agent implemented in alphagozero_agent.py to perform MCTS using PolicyValueNetwork, which we implemented just now.
Monte Carlo tree search
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.
