GitHub - KernelBypass/Pacman-AI-3: Implemented value iteration and Q-learning (with epsilon-greedy action selection) for the Pacman game agent.

Project 3 - Reinforcement Learning for UC Berkeley's CS 188 | Introduction to Artificial Intelligence

Implemented value iteration and Q-learning (with epsilon-greedy action selection) for the game agents.

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
layouts		layouts
test_cases		test_cases
README.md		README.md
VERSION		VERSION
analysis.py		analysis.py
autograder.py		autograder.py
crawler.py		crawler.py
environment.py		environment.py
featureExtractors.py		featureExtractors.py
game.py		game.py
ghostAgents.py		ghostAgents.py
grading.py		grading.py
graphicsCrawlerDisplay.py		graphicsCrawlerDisplay.py
graphicsDisplay.py		graphicsDisplay.py
graphicsGridworldDisplay.py		graphicsGridworldDisplay.py
graphicsUtils.py		graphicsUtils.py
gridworld.py		gridworld.py
keyboardAgents.py		keyboardAgents.py
layout.py		layout.py
learningAgents.py		learningAgents.py
mdp.py		mdp.py
pacman.py		pacman.py
pacmanAgents.py		pacmanAgents.py
projectParams.py		projectParams.py
qlearningAgents.py		qlearningAgents.py
reinforcementTestClasses.py		reinforcementTestClasses.py
testClasses.py		testClasses.py
testParser.py		testParser.py
textDisplay.py		textDisplay.py
textGridworldDisplay.py		textGridworldDisplay.py
util.py		util.py
valueIterationAgents.py		valueIterationAgents.py