This project is a part of:
Deep Reinforcement Learning Nanodegree
The project uses DQN algorithm to solve 'Banana' environment to maximize number of gathered yellow bananas and avoiding blue bananas.
Below you can find a list of requirements required to run train.py & play.py scripts
- python 3.6
- Banana app (this is delivered by Udacity Team)
- Linux: click here
- Mac OSX: click here
- Windows (32-bit): click here
- Windows (64-bit): click here
- torch
- numpy
- tqdm
- unityagents
python3 train.py
python3 play.py
Implementation approach & details and metrics can be found in report file.