Media Summary: In this project an agent is a two link arm wich end effector will be track an spherical volume in the space. Udacity Deep Reinforcement Learning Nanodegree - Navigation Agent trained to fetch the yellow bananas and avoid the blue ones, using the DQN algorithm discussed in this paper.
Udacity Deep Reinforcement Learning Continuous - Detailed Analysis & Overview
In this project an agent is a two link arm wich end effector will be track an spherical volume in the space. Udacity Deep Reinforcement Learning Nanodegree - Navigation Agent trained to fetch the yellow bananas and avoid the blue ones, using the DQN algorithm discussed in this paper. DRL - Multi-Agent DDPG Algorithm - Tennis Collaboration Using the Unity agent/environment "Tennis", this This video shows the evolution of two RL agents as they learn to play tennis. Github repo: ...