Deep Reinforcement Learning Nanodegree

My solutions to the projects (and mini-projects) of Udacity's Deep Reinforcement Learning Nanodegree program.

Chapters

🧪 Chapter 1: Introduction to Deep Reinforcement Learning
Notes of Chapter 1 - 'Chapter1.MD'

🧪 Chapter 2: Value-Based Methods
Notes of Chapter 2 - 'Chapter2.MD'

🧪 Chapter 3: Policy-Based Methods
Notes of Chapter 3 - 'Chapter3.MD'

🧪 Chapter 4: Multi-Agent Reinforcement
Notes of Chapter 4 - 'Chapter4.MD'

Projects

📥 Project 1: Navigation - Project 1 directory

Goal: train an agent to navigate (and collect bananas!)
Reward: +1 (Yellow banana) and -1 (Blue banana)
Actions:

• 0 - move forward.
• 1 - move backward.
• 2 - turn left.
• 3 - turn right.

Environment: dependencies, unity banana (unity-ml-agent)

The state space has 37 dimensions and contains the agent's velocity, along with ray-based perception of objects around the agent's forward direction. The task is episodic, and in order to solve the environment, the agent must get an average score of +13 over 100 consecutive episodes.

Getting Started

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

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

   (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 to obtain the environment.

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

Requirements for Udacity:

• Training Code [Navigation.ipynb], Framework use - PyTorch and Python 3, Saved Model Weights [model.pt]
• [Report.pdf] with Learning Algorithm, Plot of Rewards and Ideas for future Algorithm
• [Extra] Implement a double DQN, a dueling DQN, and/or prioritized experience replay!

Follow the instructions in Navigation.ipynb to get started with training the agent! Here's my report and here's the YouTube video of my trained agent!

(Optional) Challenge: Learning from Pixels

📥 Project 2: Continuous Control
We will work with the Unity reacher environment.

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.

Real World:

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.

Solving the Environment

Note that your project submission need only solve one of the two versions of the environment.

Option 1: Solve the First Version

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

Option 2: Solve the Second Version

The barrier for solving the second version of the environment is slightly different, to take into account the presence of many agents. In particular, your agents must get an average score of +30 (over 100 consecutive episodes, and over all agents). Specifically,

• After each episode, we add up the rewards that each agent received (without discounting), to get a score for each agent. This yields 20 (potentially different) scores. We then take the average of these 20 scores.
• This yields an average score for each episode (where the average is over all 20 agents).

The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30.

Getting Started

1. 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

   • Version 2: Twenty (20) Agents

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

   (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.)

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

Instructions

Follow the instructions in Continuous_Control-single-agent.ipynb to get started with training your own agent!

(Optional) Challenge: Crawl

📥 Project 3: Collaboration and Competition

In this project, the Tennis environment is explored.

In this environment, two agents control rackets to bounce a ball over a net. If an agent hits the ball over the net, it receives a reward of +0.1. If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of -0.01. Thus, the goal of each agent is to keep the ball in play.

The observation space consists of 8 variables corresponding to the position and velocity of the ball and racket. Each agent receives its own, local observation. Two continuous actions are available, corresponding to movement toward (or away from) the net, and jumping.

The task is episodic, and in order to solve the environment, your agents must get an average score of +0.5 (over 100 consecutive episodes, after taking the maximum over both agents). Specifically,

• After each episode, we add up the rewards that each agent received (without discounting), to get a score for each agent. This yields 2 (potentially different) scores. We then take the maximum of these 2 scores.
• This yields a single score for each episode.

The environment is considered solved, when the average (over 100 episodes) of those scores is at least +0.5.

Getting Started

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

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

   (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 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.)

2. Place the file in the DRLND GitHub repository, in the p3_collab-compet/ folder, and unzip (or decompress) the file.

Instructions

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

(Optional) Challenge: Play Soccer