For this project, the task is to train an agent to navigate (and collect bananas!) in a large, square world.
-
State space has 37 dimensions and contains the agent's velocity, along with ray-based perception of objects around agent's forward direction.
-
Action space is 4 dimentional. Four discrete actions are available, corresponding to:
0- move forward.1- move backward.2- turn left.3- turn right.
-
Reward 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.
-
Solution criteria The task is episodic, and in order to solve the environment, the agent must get an average score of +13 in fewer than 1800 episodes.
-
Configure a Python 3.6 / PyTorch 0.4.0 environment with the needed requirements as described in the Udacity repository
-
Install "unityagents" click here
-
Download the Banana 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.
-
Finally, unzip the environment archive in the 'project's environment' directory and eventually adjust thr path to the UnityEnvironment in the code.
Execute the provided notebook Navigation.ipynb (The headless / no visualization version of the Unity environment was used)