Repo containing my complete solutions to Berkley's CS188, an online course on Artificial Intelligence.
Solutions are written in Python.
Course can be found on (edX)[https://courses.edx.org/courses/BerkeleyX/CS188x_1/1T2013/info].
- Build general search algorithms for the Pacman universe to allow route planning for a given destination or multiple.
- Design agents for the classic version of Pacman, both Pacman and the Ghosts. Key learnings: minimax and expectimax search and evaluation function design.
- Implement value iteration and Q-learning for Pacman.
- Desing Pacman agents that use sensors to locate and eat invisible ghosts based on inference using Bayes' Nets.
- Design three classifiers: perceptron classifier, large-margin (MIRA) classifier and a slightly modified perceptron classifier for behavioural cloning.