Assignment #6
Due on Github 23:59 Wednesday 20 September
The sweep of the pendulum had increased in extent by nearly a yard. As a natural consequence, its velocity was also much greater.
– E.A. Poe, The Pit and the Pendulum
Objectives
-
- Expand our Deep Reinforcement Learning toolkit to enable continuous control for robotics.
- Improve our understanding of Actor/Critic methods
Running on a workstation in the Advanced Lab (Parmly 413)
Because of the computational power needed for DRL, you will want to do this assignment on a computer with a GPU. Here’s what you need to do to get started
USE YOUR ppo.py to have students write pendulum_train.py, pendulum_test.py