This repository contains the implementation of a deep reinforcement learning agent, trained with a deep Q-Network algorithm similar to the one of the Nature paper Playing Atari with Deep Reinforcement Learning. The objective of the agent is to solve one of the Unity's environment, in concrete the "Banana Collector" environment.
In this environment the agent moves to collect bananas. It will receive a positive reward each time the agent collects a yellow banana, and a negative reward if it collects a blue banana. See more information in the section Environment details.
The agent is implemented and trained in the notebook Navigation.ipynb
where the agent uses as state input the processed information given by the environment (e.g. distance to bananas, speed, direction, etc).
For a report on the results, check the following link.
The agent will interact with a simplified version of the Banana Collector environment.
The following has been extracted from the materials of the Udacity Deep Reinforcement Learning course.
A reward of +1 is provided for collecting a yellow banana, and a reward of -1 is provided for collecting a blue banana. Thus, the goal of your agent is to collect as many yellow bananas as possible while avoiding blue bananas.
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.
Given this information, the agent has to learn how to best select actions. Four discrete actions are available, corresponding to:
0 - move forward. 1 - move backward. 2 - turn left. 3 - turn right.
The task is episodic, and in order to solve the environment, your agent must get an average score of +13 over 100 consecutive episodes.
To be able to run the notebooks, one needs to prepare the environment and download the Unity environment.
As described in the Udacity github repo, to set up your python environment, follow the instructions below.
-
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
-
Follow the instructions in this repository to perform a minimal install of OpenAI gym.
-
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 .
- Create an IPython kernel for the
drlnd
environment.
python -m ipykernel install --user --name drlnd --display-name "drlnd"
- Before running code in a notebook, change the kernel to match the
drlnd
environment by using the drop-downKernel
menu.
Select and download the environment that matches your operating system:
Linux: click here
Mac OSX: click here
Windows (32-bit): [click here(]https://s3-us-west-1.amazonaws.com/udacity-drlnd/P1/Banana/Banana_Windows_x86.zip)
Windows (64-bit): click here
Then, place the file in the p1_navigation/
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 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.)
Once your environment is set-up, just run the notebooks Navigation.ipynb
.