Skip to content

behinoo/Controlling-a-Double-jointed-Arm-using-Reinforcement-Learning

Repository files navigation

Controlling-a-Double-jointed-Arm-using-Reinforcement-Learning

Introduction

This project was inspired by Mahmood et al. paper

Video Training robotic arm to reach target location YouTube

This project use Reacher environment.

Trained Agent

In this environment, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of the agent is to maintain its position at the target location for as many time steps as possible.

The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1.

Distributed Training

For this project, we will provide you with two separate versions of the Unity environment:

  • The first version contains a single agent.
  • The second version contains 20 identical agents, each with its own copy of the environment.

The second version is useful for algorithms like PPO, A3C, and D4PG that use multiple (non-interacting, parallel) copies of the same agent to distribute the task of gathering experience.

Instructions

Installation

  1. Download the environment from one of the links below. You need only select the environment that matches your operating system:

    (For Windows users) Check out this link if you need help with determining if your computer is running a 32-bit version or 64-bit version of the Windows operating system.

This project used some of the components of the many components of the codes provided by Udacity to solve OpenAI Gym's Pendulum environment.

List of files:

  • Continuous_Control.ipynb
  • ddpg_agent.py
  • model.py

Run Continuous_Control.ipynb to start.

About

In this environment, a double-jointed arm can move to target locations.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published