Drlnd Continuous Control

Summary

Introduce the Udacity Deep Reinforcement Learning Project 2: This is the second project of the Deep Reinforcement Learning Nanodegree. I trained a DDPG Agent to solve the Reacher ... In this project, we work with Reacher ... In this project an agent is a two link arm wich end effector will be track an spherical volume in the space. ... up and I'm going to talk today about data data decisions deep reinforcement learning for Agent in "reacher" environment trained to reach the ball using deep reinforcement learning (deep deterministic policy gradient ... Autonomous object avoidance using from raw pixels. In this video the car has learned to avoid objects using the deep ...