#Machine Learning Nano Degree
- Identified states that model the driving agent and environment, along with a sound justification.
- Implemented Q-Learining algorithm for driving agent to choose the best action.
- Implemented epsilon-greedy strategy in order to search all the state space.
- Tuned parameters of Q-Learning to find the optimal policy.
- Leveraged reinforcement techniques to train a smartcab how to drive in an idealized grid-like city, with roads going North-South and East-West.
The content of this repository is licensed under MIT License