AleksandarHaber / SARSA-Temporal-Difference-Learning-in-Python

These code files implement the on-policy SARSA (State-Action-Reward-State-Action) reinforcement learning algorithm in Python.

SARSA-Temporal-Difference-Learning-in-Python

These code files implement the on-policy SARSA (State-Action-Reward-State-Action) reinforcement learning algorithm in Python. To test the code, we use the Frozen Lake OpenAI Gym environment. You can also use the Gymnasium environment, for more details, see "driverCode.py" The webpage explaning the codes and the SARSA Temporal difference learning is given here:

https://aleksandarhaber.com/explanation-and-python-implementation-of-on-policy-sarsa-temporal-difference-learning-reinforcement-learning-tutorial/

The YouTube tutorial is given here:

https://www.youtube.com/watch?v=ZXEVznd5kaM

Explanation of the code files:

• "functions.py" - definition of the class "SARSA_Learning" that implements the SARSA temporal difference learning algorithm
• "driverCode.py" - driver code that explains how to use "SARSA_Learning" class