First project in the Udacity nano degree - Train an agent to navigate (and collect bananas!) in a large, square world.
Environment Info :
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.
-
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
-
Place the file in this GitHub repository, in the folder, and unzip (or decompress) the file.
-
Install the requirements from the python folder using
pip install ./python- Since most people might run into errors for torch 0.4.0, i removed it from the requirements and torch needs to be installed separately.
Follow the code cells in Navigation.ipynb after the tutorial to train the agent!
- Load the trained agent weights from the
checkpoints.pthfile to see the agent in action