This is the code for Deep Reinforcement Learning Nano Degree's first project. The aim of the project is to train an intelligent agent to walk around and collect bananas in a large, square world.
There are yellow and blue bananas in the simulator environment, and the agent is supposed to collect as many yellow bananas as possible while avoiding collecting the blue bananas.
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 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.
-
Follow instructions in nanodegree's prerequisite to set up the the required packages and modules.
-
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 environment.
-
Place the file in the DRLND GitHub repository, in the
p1_navigation/
folder, and unzip (or decompress) the file.
Use TrainNetwork.ipynb
to train the agent and use saved network weights to see the performance of the agent.
(For AWS) If you'd like to train the agent on AWS, you must follow the instructions to set up X Server, and then download the environment for the Linux operating system above.