课程简介
This course builds on introductory topics in game and puzzle algorithms (e.g., CMPUT 390) and focuses on advanced methods for intelligent decision-making that integrate search, knowledge, and simulation.
Students will study how classical search techniques can be extended with probabilistic reasoning, machine learning, and large-scale simulation. The course emphasizes modern approaches such as Monte Carlo Tree Search (MCTS), reinforcement learning, and neural networks, and examines how these methods are combined in state-of-the-art systems such as AlphaGo and AlphaZero.
Through programming assignments and experimental evaluation, students will design, implement, and analyze intelligent agents capable of making complex decisions in competitive environments.
