🚀 Deep Reinforcement Learning Nanodegree

This nanodegree program by Udacity consists of 4 courses - Foundations of Reinforcement Learning, Value-Based Methods, Policy-Based Methods, Multi-Agent Reinforcement Learning - to learn cutting-edge deep reinforcement learning algorithms from Deep Q-Networks (DQN) to Deep Deterministic Policy Gradients (DDPG) and apply these concepts to train agents to walk, drive, or perform other complex tasks.

The 3 projects I completed as part of this nanodegree:

• Navigation Project

• Continuous Control Project

• Collaboration and Competition Project

Getting Started

First clone this repository. To set up your python environment, follow the instructions below.

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

python -m ipykernel install --user --name drlnd --display-name "drlnd"
conda create --name drlnd python=3.6 
activate drlnd

2. Follow the instructions in this repository to perform a minimal install of OpenAI gym.

   • Next, install the classic control environment group by following the instructions here.
   • Then, install the box2d environment group by following the instructions here.

   pip install gym

3. Install several dependencies

conda install Pillow matplotlib numpy jupyter pytest docopt pyyaml protobuf grpcio pandas scipy ipykernel
conda install -y pytorch -c pytorch
pip install tensorflow==2.2.0rc4
pip install unityagents

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

   Project 1: Navigation

   

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

   Project 2: Continuous Control: Reacher environment.

   

   • One (1) Agent
     • Linux: click here
     • Mac OSX: click here
     • Windows (32-bit): click here
     • Windows (64-bit): click here

   Project 3: Collaboration and Competition Tennis environment.

   

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

5. Place the environment file in the corresponding project folder navigation/ or continuous-control/ or collab-compet/ and unzip (or decompress) the file.

6. Follow the instructions in Navigation.ipynb / Continuous_Control.ipynb / Tennis.ipynb to get started with training your own agent!