Tags: #python

MDPs, Bellman equations, batch value iteration, tabular Q-learning with epsilon-greedy exploration, and approximate Q-learning with feature weights.

Multi-agent search in Pacman. Minimax with depth-limited game trees, alpha-beta pruning, expectimax for random ghosts, and evaluation functions.

Implementing graph search algorithms in the Berkeley Pacman framework. DFS, BFS, UCS, A*, plus heuristics for corners and food.