Name | ID |
---|---|
Habib Gemmechu | UGR/4012/12 |
Liban Abduba | UGR/3781/12 |
Samuel Girma | UGR/6303/12 |
Endale Yohannes | UGR/7379/12 |
Using a Q-Learning formula we can help the agent find the rewards, positive and negative, of driving routes for the passengers. Then with this knowledge it will continually improve over time all without any intervention.
pip
(Python package installer)Clone the repository:
git clone https://github.com/habib-gm/Taxi-Driving-reinforcement-learning-project-a-virtual-autonomous-taxi.git
cd Taxi-Driving-reinforcement-learning-project-a-virtual-autonomous-taxi ```
install requirements:
pip install -r requirements.txt
Usage:
python agent_10000_trials.py