Question

Modify the values for the exploration factor, discount factor, and learning rates in the code to understand how those values affect the performance of the algorithm. Be sure to place each experiment in a different code block so that your instructor can view all of your changes.

Note: Discount factor = GAMMA, learning rate = LEARNING_RATE, exploration factor = combination of EXPLORATION_MAX, EXPLORATION_MIN, and EXPLORATION_DECAY.

Answer 1

The question involves adjusting the exploration factor, discount factor, and learning rate in a Q-learning algorithm to observe their effects on its performance.

Step-by-step explanation:

The subject of the question concerns the tuning of hyperparameters in reinforcement learning, specifically within the context of a Q-learning algorithm. The exploration factor, discount factor (GAMMA), and learning rate (LEARNING_RATE) are critical values that influence the algorithm's decision-making process and its ability to learn from the environment over time.

By adjusting the exploration factor values (EXPLORATION_MAX, EXPLORATION_MIN, and EXPLORATION_DECAY), we dictate the balance between exploration of new actions and exploitation of known ones. Tweaking the discount factor affects how future rewards are valued relative to immediate ones.

Lastly, modifying the learning rate determines the extent to which new information overrides old information. It's crucial to place each set of experiments in a separate code block to isolate the effects of the changes and to enable clear analysis by the instructor.

Each hyperparameter adjustment should be conducted in separate code blocks for clear analysis.