Monte Carlo Tree Search Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

The evolution of MCTS from its origins in Go to modern planning and environment design.

Monte Carlo Tree Search: 10 key papers

1. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
   Schrittwieser et al. arXiv 2019.
2. Monte-Carlo Tree Search as Regularized Policy Optimization
   Grill et al. arXiv 2020.
3. Thinking Fast and Slow with Deep Learning and Tree Search
   Anthony et al. arXiv 2017.
4. Learning to Search with MCTSnets
   Guez et al. arXiv 2018.
5. Learning and Planning in Complex Action Spaces
   Hubert et al. arXiv 2021.
6. Bandit Algorithms for Tree Search
   Coquelin and Munos. arXiv 2007.
7. Single-Agent Optimization Through Policy Iteration Using Monte-Carlo Tree Search
   Seify and Buro. arXiv 2020.
8. Vector Quantized Models for Planning
   Ozair et al. arXiv 2021.
9. Online and Offline Reinforcement Learning by Planning with a Learned Model
   Schrittwieser et al. arXiv 2021.
10. Dual Monte Carlo Tree Search
    Kadam et al. arXiv 2021.

Related reading lists

• Classical Planning & Search Algorithms
• Model-Based Reinforcement Learning
• World Models and Model-Based RL
• Neural Architecture Search
• Unsupervised Environment Design
• Bayesian Optimization & Global Optimization
• Self-Play & Population-Based Training
• Meta-Reinforcement Learning