This is the 2nd Coursework for F29AI Artificial Intelligence and Intelligent Agents, 3rd year of Bsc Computer Science. This coursework consists of 3 parts, one written in Java, and the two last parts where done as a class test.
The program written in Java is the game TicTacToe. The algorithms written for this coursework is Value Iteration, Policy Iteration and Q-Learning with Epsilon Greedy Policy.
The source code for this program has been encrypted due to the coursework being still used.
TicTacToe: CW2_Part1_TicTacToe_in_Java.zip Solutions to part 2 and 3: CW2-Part2and3.zip
If you want to have a look at the code, password can be requested from wrt_95@hotmail.com.