World Models Handbook
Search and Belief-Space Planning
Covers MCTS, UCT, PUCT, belief-space planning, and POMCP for decision-making under uncertainty with a hidden-state maze and tiger problem.
86 min read
Data & AI, Private Equity, Technology.
Experienced analytics, AI, and technology leader with 13+ years of experience across data science, private equity, management consulting, entrepreneurship, and software engineering. Sharing thoughts on these topics.
Latest writing
Search and Belief-Space Planning
Covers MCTS, UCT, PUCT, belief-space planning, and POMCP for decision-making under uncertainty with a hidden-state maze and tiger problem.
Differentiable Planning
Explains how gradients flow through world-model rollouts, from adjoint backpropagation to action optimization, terminal values, and long-horizon stability.
Sampling-Based Planning and Model Predictive Control
Explains how sampling-based planning and model predictive control turn black-box world models into controllers, using random shooting, CEM.
Pretraining, Post-Training, Scaling, and Adaptation
Explains how world models are pretrained on diverse data, post-trained with preference objectives.
Online, Offline, and Continual Learning
Explains how world models adapt over time through offline, online, and continual learning, covering replay, catastrophic forgetting, and safe drift guardrails.
Data Curation and Synthetic Data
Curation determines what a world model can learn. Examines deduplication, filtering, balancing, synthetic data, mixture weights, and contamination risks.
Panel discussion · Singapore
About
Making data and AI useful
Speaking with investors and operators about choosing problems worth solving, understanding what the technology can really do, and making it work in practice.
Commercial judgment · Technical depth
More about meNewsletter
Stay up to date
Get articles, book updates, and news delivered to your inbox.
No spam, unsubscribe anytime.
Books
Complex ideas made simple through clear explanations and intuitive visuals
Machine learning and math concepts explained step by step so you can understand how it works, without hours of digging through dense textbooks. Free to read online.
World Models Handbook
Read the World Models Handbook online for free. Learn latent dynamics, model-based reinforcement learning, planning, physical AI, evaluation, and deployment.
Build a GPT from Scratch
Build a small GPT-style language model in PyTorch. Follow each step from embeddings and attention through training, optimization, and text generation.
Community
Learn with the community
Create a free account to keep your reading organized, join thoughtful discussions, and get more from every chapter.
- Keep your place across books and articles
- Ask questions and take part in discussions
- Read with fewer interruptions
Free to join · Takes less than a minute
Why
I created this space so readers can learn together, ask questions, and make sense of difficult ideas.
From readers1 / 12
Topics
Browse by category
Data, Analytics & AI
634 articles
LLM and GenAI
32 articles
Machine Learning
679 articles
Chinese
0 articles
Software Engineering
372 articles
Economics & Finance
2 articles
Entrepreneurship
0 articles
Philosophy
12 articles
Language AI Handbook
409 articles
History of Language AI
110 articles
Machine Learning from Scratch
66 articles
Build a GPT from Scratch
0 articles
AI Agent Handbook
44 articles
Quantitative Finance
79 articles