GitHub - piyush2896/Q-Learning: Q-Learning from scratch in Python

There are drawbacks, like requirement of knowing the dynamics of the environment, which we face when using techniques like Value Iteration and Policy iteration. To overcome this drawback we can use sampling-based approximation techniques like Q-Learning. The task is to maximize a reward in a world that consists of an agent that can navigate in 4 directions - North, South, East and West. With a 20% of equally likely chance of deviating to left or right from the action asked to perform. Modify main.json to suit your needs.