1. Learn
    2. /
  2. Courses
    3. /
  3. Reinforcement Learning with Gymnasium in Python
Connected

Exercise

Applying double Q-learning

This exercise tasks you with applying the Double Q-learning algorithm in the same custom environment you solved with Expected SARSA to investigate the difference. Double Q-learning, by using two Q-tables, helps reduce the overestimation bias inherent in the traditional Q-learning algorithm and offers more stability in learning than other temporal difference methods. You'll use this method to navigate through the grid environment, aiming for the highest reward while avoiding mountains in order to reach the goal as quickly as possible.

new_cust_env.png

Instructions

100 XP
  • Update the Q-tables using the update_q_tables() function you coded in the previous exercise.
  • Combine the Q-tables by summing them.