For this project, we will train an agent to navigate (and collect bananas!) in a large, square world.
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.
You can play the game executing the notebook: Navigation-Human.ipynb
.
-
The respository contains Mac OSX version of Banana Game. If you need other environments select the one 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 repository, and unzip it. You also need to install Unity ML-Agents.
-
Run the notebook
Navigation-Random-Agent.ipynb
.
In order to train the model run Navigation-Training.ipynb
. The model is located in model.py
and the agent in dqn_agent.py
.
By running Navigation-Trained-Agent.ipynb
you can watch how trained agent is playing.
This is the first project of the Deep Reinforcement Learning Nanodegree.
The agent mostly comes from Exercise 6 of Lesson Deep Q Agent.