Awesome Monte Carlo Tree Search
A curated collection of Monte Carlo tree search research papers with implementations from top AI conferences.
What is Awesome Monte Carlo Tree Search?
Awesome Monte Carlo Tree Search Papers is a curated GitHub repository that collects academic research papers on Monte Carlo Tree Search (MCTS) along with their code implementations. It addresses the problem of fragmented access to cutting-edge MCTS research by providing a centralized, organized list of papers from top-tier AI conferences and journals. The repository helps researchers and engineers quickly discover relevant work and available code for applications ranging from game playing to automated theorem proving.
AI researchers, graduate students, and machine learning engineers who are exploring or applying Monte Carlo Tree Search algorithms in areas like reinforcement learning, robotics, automated reasoning, or game theory. It is particularly valuable for those seeking reproducible research with accessible implementations.
Developers choose this repository because it saves significant time in literature review by aggregating high-quality MCTS papers with code links in one place. Its unique value lies in the combination of rigorous academic curation (focusing on top conferences) and practical utility (including implementations), which is not typically found in standard academic databases or generic paper lists.
Overview
A curated list of Monte Carlo tree search papers with implementations.
Use Cases
Best For
- Finding recent Monte Carlo Tree Search papers with open-source implementations
- Exploring MCTS applications in reinforcement learning and game AI
- Researching MCTS for combinatorial optimization and black-box optimization
- Studying the integration of MCTS with large language models for reasoning tasks
- Comparing MCTS algorithms across different domains like robotics, vision, or NLP
- Accessing a historical overview of MCTS research from foundational to state-of-the-art work
Not Ideal For
- Developers seeking plug-and-play MCTS libraries for immediate commercial integration
- Beginners needing step-by-step tutorials or introductory guides on MCTS fundamentals
- Projects requiring real-time support, documentation, or production-ready code examples
- Teams focused solely on applied AI without academic research context or literature review
Pros & Cons
Pros
Aggregates papers exclusively from premier venues like NeurIPS, ICML, and AAAI, ensuring access to high-quality, peer-reviewed research.
Includes direct links to code repositories for many papers, aiding reproducibility and practical application, as seen in entries from 2018-2020 with GitHub links.
Organizes papers chronologically from 2025 back to 1988, providing a comprehensive timeline of MCTS evolution and key trends.
Spans diverse fields like robotics, NLP, CV, and game AI, making it a versatile resource for interdisciplinary research.
Cons
Many recent entries (e.g., 2025 papers) have empty code links, limiting immediate usability for replication and requiring additional search efforts.
Lists papers without ratings, reviews, or summaries, forcing users to independently evaluate relevance, methodology, and results.
Focuses on conference and journal papers, potentially missing industry reports, blog posts, or less formal but practical resources.
Frequently Asked Questions
Related Projects
vintaAn opinionated list of Python frameworks, libraries, tools, and resources
awesome-machine-learningA curated list of awesome Machine Learning frameworks, libraries and software.
awesome-awesomenessA curated list of awesome awesomeness
data-science-ipython-notebooksData science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.