AleksandarHaber / Greedy-in-the-Limit-with-Infinite-Exploration-GLIE-Monte-Carlo-Reinforcement-Learning-in-Python

The Python codes given here, explain how to implement the Greedy in the Limit with Infinite Exploration (GLIE) Monte Carlo Control Method in Python. We use the OpenAI Gym (Gymnasium) to test the Python codes. More precisely we use the Frozen Lake Environment to test the GLIE Monte Carlo Control method.

Greedy-in-the-Limit-with-Infinite-Exploration-GLIE-Monte-Carlo-Reinforcement-Learning-in-Python

The Python codes given here explain how to implement the Greedy in the Limit with Infinite Exploration (GLIE) Monte Carlo Control Method in Python. We use the OpenAI Gym (Gymnasium) to test the Python codes. More precisely we use the Frozen Lake Environment to test the GLIE Monte Carlo Control method. The uploaded code files are used in a tutorial on Reinforcement Learning. The reinforcement tutorial webpage explaining the uploaded codes and the GLIE Monte Carlo Control method is given here:

https://aleksandarhaber.com/python-implementation-of-the-greedy-in-the-limit-with-infinite-exploration-glie-monte-carlo-control-method-reinforcement-learning-tutorial/

Uploaded code files:

• functions.py - is the file containing the function "MonteCarloControlGLIE()" that implements the GLIE Monte Carlo control method.

• driverCode.py - is the driver code that explains how to use the function "MonteCarloControlGLIE()" and that explains how to simulate and visualize the learned policy.