Final Project - Reinforcement Learning V/S Imitation Learning

Computational Intelligence - Spring '19 - Habib University

• For a quick video demonstration, view the provided "Demonstration.mp4" or refer to: https://youtu.be/iJlEbHsgM7Q
• For the final report, refer to "Final Report.pdf" - also provided.

Dependencies/Versions:

• Python 3.6.8
• OpenAI GYM 0.12.1
• Mujoco200 Linux
• Mujoco_py 2.0.2.2
• Tensorflow 1.13.1

Tested in Linux Mint 18.3 (Sylvia)

Acknowledgements:

Credits to open-source coursework for CS294-112: Deep Reinforcement Learning for inspiration and expert policies.

Author(s):

• Osama Yousuf - BS(CS) - oy02945
• Reeba Aslam - BS(CS) - ra02528