Columbia University, NY                                                                March 2022 - May 2022

​

Description:

• A class project for practicing reinforcement learning

• The problem is to calculate the arm's joint torques from states of each step, and drive the end effector to the target point.

• The project consists 4 parts:

  • Implemented model predictive control (MPC)

  • Use DNN to learn dynamics

  • Implemented deep Q-network (DQN)

  • Implemented the environment and used proximal policy optimization (PPO) from stable-baselines3 library