Monte Carlo Tree Search: An Introduction | by Benjamin Wang | Towards Data Science

MCTS is the cornerstone of AlphaGo and many AI applications. We aim to build some intuitions and along the way get our hands dirty.

Monte Carlo Tree Search: An Introduction | Towards Data Science Machine Learning Monte Carlo Tree Search: An Introduction MCTS is the cornerstone of AlphaGo and many AI applications. We aim to build some intuitions and along the way get our hands dirty. Benjamin Wang Jan 10, 2021 6 min read Share Monte Carlo (Image from Unsplash ) Monte Carlo Tree Search (MCTS) is an important algorithm behind many major successes of recent AI applications such as AlphaGo’s striking showdown in 2016. In this blog, we will first start with uninformed search in which we simply traverse through the whole se

saved by

• Alexander De Biasio

related reading

• Monte Carlo tree search - Wikipediaen.wikipedia.org
• Alpha–beta pruning - Wikipediaen.wikipedia.org
• [1901.10995] Go-Explore: a New Approach for Hard-Exploration Problemsar5iv.labs.arxiv.org
• Simple Alpha Zeroweb.stanford.edu
• The Multi-Armed Bandit Problem and Its Solutions | Lil'Loglilianweng.github.io
• AlphaGo Zero: Minimal Policy Improvement, Expectation Propagation and other Connectionsinference.vc
• Chess Engines: A Zero to One Guidechessengines.super.site
• Principal variation search - Wikipediaen.wikipedia.org
• Breadth-first search - Wikipediaen.wikipedia.org
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• Monte Carlo Tree Search with Spectral Expansion for Planning with Dynamical Systemsarxiv.org
• Proposal: Using Monte Carlo tree search instead of RLHF for alignment research — LessWronglesswrong.com