tomgtqq/deep-reinforcement-learning-continuous-control

Udacity drlnd project2

deep-reinforcement-learning-continuous-control

Distributed Training robotic-arm can move to target locations using actor-critic DDPG.

Introduction

For this project, Training 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.

Agents must get an average score of +30 (over 100 consecutive episodes, and over all agents).The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30.

Real World

Having multiple copies of the same agent sharing experience can accelerate learning.

Simulation Environment

Unity Machine Learning Agents (ML-Agents) is an open-source Unity plugin that enables simulations to serve as environments for training intelligent agents. For this project, work with the Reacher environment.

Getting Started

The Project is for Udacity Deep Reinforcement learning nd.

Download the Unity Environment

• Linux: click here
• Mac OSX: click here
• Windows (32-bit): click here
• Windows (64-bit): click here

Dependencies

1. Create (and activate) a new environment with Python 3.6.

   • Linux or Mac:

   conda create --name drlnd python=3.6
   source activate drlnd

   • Windows:

   conda create --name drlnd python=3.6 
   activate drlnd

2. Clone the repository (if you haven't already!), and navigate to the python/ folder. Then, install several dependencies.

git clone https://github.com/udacity/deep-reinforcement-learning.git
cd deep-reinforcement-learning/python
pip install .

3. Create an IPython kernel for the drlnd environment.

python -m ipykernel install --user --name drlnd --display-name "drlnd"

4. Before running code in a notebook, change the kernel to match the drlnd environment by using the drop-down Kernel menu.

Running

conda activate drlnd

jupyter notebook 

Then select Continuous_Control.ipynb and running

Versioning

We use SemVer for versioning. For the versions available, see the tags on this repository.

Built With

• Udacity - Udacity Deep Reinforcement learning nd
• Unity - Unity ML-Agents Toolkit Documentation

Resources

• Continuous Control With Deep Reinforcement Learning(DDPG)
• Proximal Policy Optimization Algorithms(PPO)
• Asynchronous Methods for Deep Reinforcement Learning(A3C)
• Distributed Distributional Deterministic Policy Gradients(D4PG)
• Benchmarking Deep Reinforcement Learning for Continuous Control
• Openai Baselines

Authors

• Tom Ge - Fullstack egineer - github profile

License

This project is licensed under the MIT License