This is the collection of class assignments for CSE 511A: Introduction to Artificial Intelligence – Fall 2017 in Washington University. It is based on CS188 at UC Berkeley.
Help Pacman agent to find paths through his maze world, both to reach a particular location and to collect food efficiently.
- Depth-first search (DFS)
- Breadth-first search (BFS)
- Uniform-cost graph search
- A* graph search
- Implement a search problem CornersProblem
- Implement a consistent, non-trivial heuristic for CornersProblem
- Implement a consistent, non-trivial heuristic for FoodSearchProblem
- Suboptimal search
Design agents for the classic version of Pacman, including ghosts.
- Reflex agent
- Minimax agent
- Alpha-beta pruning
- Expectimax agent
- Better evaluation function
Implement value iteration and Q-learning.
- Value iteration
- Value iteration: parameter tuning #1
- Value iteration: parameter tuning #2
- Q-learning
- Q-learning: epsilon-greedy
- Q-learning: parameter tuning
- Q-learning: crawler
- Q-learning: training
- Approximate Q-learning
Design Pac-Man agents that use sensors to locate and eat invisible ghosts.
- Exact inference: stationary
- Exact inference: moving
- Greedy action
- Particle filtering
- Joint particle filtering: Bayesian network #1
- Joint particle filtering: Bayesian network #2