Back to index
OtherA full semester of lectures plus the famous Pacman projects·Free (materials and lecture videos are open)

Berkeley CS188: Introduction to Artificial Intelligence

4.7

Still one of the best structured introductions to classical AI anywhere, and the Pacman projects are the reason people remember it years later. This is the course that teaches you how an agent reasons, plans, and acts under uncertainty.

What We Liked

  • The Pacman projects are genuinely excellent, you implement search, adversarial play, and reinforcement learning yourself
  • Covers the foundations that the deep learning hype skips over, search, MDPs, Bayes nets, and HMMs
  • Free and open, with full lecture videos, slides, and autograded assignments
  • Taught by people who shaped the field, so the framing is authoritative

What Could Be Better

  • It is a classical AI course, so modern deep learning and large language models get only a brief treatment
  • Self-studying the projects without the course staff means debugging is on you
  • The probability and search material demands real focus, this is not a casual watch

Detailed review

CS188 is the course I point people to when they say they want to understand AI from the ground up rather than just use a model someone else trained. It teaches the part of the field that does not go out of date, how an agent searches a space of possibilities, how it plans against an opponent with minimax and alpha-beta pruning, how it makes decisions under uncertainty with Markov decision processes and reinforcement learning, and how it reasons about probability with Bayes nets and hidden Markov models. The reason it has lasted is the Pacman project series. Instead of toy exercises you build the actual logic that drives an agent through a maze, first with uninformed and heuristic search, then adversarial search, then value iteration and Q-learning, and the autograder gives you that satisfying click of knowing your implementation is correct.

Doing the work yourself is what turns these from abstract ideas into things you genuinely understand, and it is hard to overstate how much better that is than watching someone explain them. The lecturers built much of this material, so the explanations are clear and the framing is the one the field actually uses. The honest limitation is scope. This is classical AI, so deep learning and the large language models everyone talks about now are touched on rather than taught in depth, and if you came expecting to build a chatbot you will be surprised.

You also feel the absence of course staff when you self-study, because a stuck project is yours to untangle. But none of that changes the verdict. The foundations here make everything else you learn afterward make more sense, and I would happily send any serious beginner through CS188 first and a modern deep learning course second.

[ final ]

The verdict.

If you want to understand how AI agents actually reason rather than just call an API, this is the course to take. Pair it with a modern deep learning course afterward and you have both the timeless foundations and the current techniques.