- Unzip MDP.zip to get working grids
- run "java-jar rl_sim.jar" to start the gui
- load big and small samples into the policy iteration
- initialize then execute to run the algorithms on the MDPs created Repeat for value iteration, q-learning algorithms
All credit for graphs and grids created go to the creators for the reinforcement learning gui, taken from https://www.cs.cmu.edu/~awm/rlsim/
Github link: https://github.com/jminowa3/MDP