In this project, several techniques of Artificial Intelligence such as Searching, Adversarial Behaviour, Deep Reinforcement Learning, Neural Network etc are implemented to help the pacman agent to maximize its expected utility.
- Project 0: Python Autograder Tutorial
- Project 1: Searching - DFS, BFS, UCS, Greedy Search, A* Search, etc.
- Project 2: MultiAgent Pacman - minimax, alpha-beta pruning, expectimax, etc.
- Project 3: Reinforcement Learning - MDP, value iteration, q-learning, epsilon-greedy, approximate q-learning, etc.
- Project 4: Ghostbusters - HMM, Particle Filtering, Bayes' Nets, Deep Reinforcement Learning, etc.
Refer project specification file under each project for more details.
Programming Language - Python 2.7