Reading Berkeley CS188 Spring 2026 through Projects P0–P5, from search and decision making to probabilistic inference, reinforcement learning, and machine learning.
CS188 Spring 2026 publishes 28 recordings, 27 lecture slide sets, 11 discussions, and Projects P0–P5. P0 is a Python/autograder tutorial, P1–P4 use Pacman settings, and P5 contains general machine-learning tasks.
Lectures 1–4 and Project 1 connect DFS, BFS, UCS, A*, state representation, and heuristic design. The goal is not memorizing algorithms but separating what the frontier, cost, and state each control.
Lectures 5–8 use CSPs to practice variables, constraints, and search order before Project 2 implements minimax, alpha-beta, and expectimax. Their key difference is the assumption made about other agents.
Lectures 9–12 and Project 3 use the same Gridworld to contrast value iteration with a known model, Q-learning from unknown dynamics, and approximate Q-learning that generalizes through features.
Lectures 13–18 and Project 4 move from factor operations and variable elimination to exact inference and particle filtering, letting Pacman track invisible ghosts through noisy distance sensors.
Lectures 19–25 connect rational decisions and VPI to machine learning, while Project 5 uses PyTorch for regression, classification, CNNs, attention, and an optional character-GPT.
Lectures 26–28 close with nuclear monitoring, AI safety, and reflection. Independent completion should preserve assumptions, test evidence, and failure analysis for Projects 1–5 instead of reporting only autograder scores.