Project 2: Continous Control

Introduction

For this project, DDPG and DDPG with priority experience replay were developed to train and evaluate a double-joined arm agent to follow target in the unity ML-agent Reacher environment. This project is part of the Deep Reinforcement Learning Nanodegree program.

Rewards

A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of DDPG and DDPG_PER agents is to maintain its position at the target location for as many time steps as possible.

Environment

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.

The task is episodic, and in order to solve the environment, the agent must get an average score of +30 over 100 consecutive episodes.

Getting Started

Download DRLND repository

To set up your python environment to run the code in this repository, follow the instructions below.

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

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 .

4. Create an IPython kernel for the drlnd environment.

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

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

Download Unity Environment

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

Version 1: One (1) Agent

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

Then, place the file in the p2_continuous-control/ folder in the DRLND GitHub repository, and unzip (or decompress) the file.

(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.

(For AWS) If you'd like to train the agent on AWS (and have not enabled a virtual screen), then please use this link (version 1) or this link (version 2) to obtain the "headless" version of the environment. You will not be able to watch the agent without enabling a virtual screen, but you will be able to train the agent. (To watch the agent, you should follow the instructions to enable a virtual screen, and then download the environment for the Linux operating system above.)

Place the file in the DRLND GitHub repository, in the p1_navigation/ folder, and unzip (or decompress) the file.

Instructions

Follow the instructions in DDPG/ and DDPG_PER/ folders to get started with training the agents agent!

Implementation Details

All implementation details and results are found in Report/ folder

References

• [1]: V. Mnih et al., "Human-level control through deep reinforcement learning", Nature, vol. 518, no. 7540, pp. 529-533, 2015. Available: 10.1038/nature14236 [Accessed 3 September 2021].
• [2]: U. Technologies, "Machine Learning Agents | Unity", Unity, 2021. [Online]. Available: https://unity.com/products/machine-learning-agents. [Accessed: 03- Sep- 2021].
• [3]: R. Sutton and A. Barto, Reinforcement Learning, 2nd ed. 2019.
• [4]: T. P. Lillicrap et al., "Continuous control with deep reinforcement learning", arXiv, vol. 150902971, 2015. [Accessed 4 October 2021].
• [5]: T. Schaul, J. Quan, I. Antonoglou and D. Silver, "Prioritized Experience Replay", arXiv, vol. 151105952, 2016. [Accessed 4 October 2021].