No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Unity Banana Navigation


Project details

Project created as 1st project on Udacity Deep Reinforcement Learning nanodegree. The goal of the agent is to gather yellow bananas while avoiding the blue ones. Here are Unity details of the environment:

Unity brain name: BananaBrain
        Number of Visual Observations (per agent): 0
        Vector Observation space type: continuous
        Vector Observation space size (per agent): 37
        Number of stacked Vector Observation: 1
        Vector Action space type: discrete
        Vector Action space size (per agent): 4
        Vector Action descriptions: , , , 

That means we work with state vector containing 37 continous values and 4 discrete actions representing moves (forward, backward, turn left, turn right). The environment is considered solved when agents reaches average score of 13.0 on 100 consecutive episodes.

Getting started

Make sure you have python 3.6 installed and virtual environment of your choosing activated. Unity has to be installed on your system. Run:

source ./

to install python dependencies. Then you should be able to run jupyter notebook and view navigation.ipynb. File contains neural network class used as a Q function and file contains agent code.


Run navigation.ipynb for further details.