iamjagdeesh/Artificial-Intelligence-Pac-Man

Implements pathfinding algorithms (DFS, BFS, A*), adversarial game-playing techniques (minimax, alpha-beta pruning), and reinforcement learning approaches (Q-learning, value iteration) across four progressive projects. The Pacman domain serves as a testbed for comparing classical search methods, multi-agent decision-making with imperfect information (HMM, particle filtering), and deep RL agents optimizing long-term utility. Built in Python 2.7 with autograded evaluation framework for each algorithmic component.

No commits in the last 6 months.