drlnd-p2-Continuous_Control

This is the 2nd project in Udacity DRLND, which is practice for training an agent that controls a robotic arm in Unity's Reacher environment using the Deep Deterministic Policy Gradients (DDPG) algorithm.

drlnd-p1-navigation

This is the 1st project in Udacity DRLND, which is practice for training an agent to collect bananas in a large, square world using Deep Q-Networks algorithm.

drlnd_p3_collab-compet

This is the 3rd project in Udacity DRLND, which is practice for training two agents that control rackets to bounce a ball over a net in Unity's Tennis environment using multi agents Deep Deterministic Policy Gradients (DDPG) algorithm.