1. Aprender
    2. /
  2. Cursos
    3. /
  3. Reinforcement Learning with Gymnasium in Python
  • 1

    Introduction to Reinforcement Learning

    Gratuito

    Dive into the exciting world of Reinforcement Learning (RL) by exploring its foundational concepts, roles, and applications. Navigate through the RL framework, uncovering the agent-environment interaction. You'll also learn how to use the Gymnasium library to create environments, visualize states, and perform actions, thus gaining a practical foundation in RL concepts and applications.

  • 2

    Model-Based Learning

    Delve deeper into the world of RL focusing on model-based learning. Unravel the complexities of Markov Decision Processes (MDPs), understanding their essential components. Enhance your skill set by learning about policies and value functions. Gain expertise in policy optimization with policy iteration and value Iteration techniques.

  • 3

    Model-Free Learning

    Embark on a journey through the dynamic realm of Model-Free Learning in RL. Get introduced to to the foundational Monte Carlo methods, and apply first-visit and every-visit Monte Carlo prediction algorithms. Transition into the world of Temporal Difference Learning, exploring the SARSA algorithm. Finally, dive into the depths of Q-Learning, and analyze its convergence in challenging environments.

  • 4

    Advanced Strategies in Model-Free RL

    Dive into advanced strategies in Model-Free RL, focusing on enhancing decision-making algorithms. Learn about Expected SARSA for more accurate policy updates and Double Q-learning to mitigate overestimation bias. Explore the Exploration-Exploitation Tradeoff, mastering epsilon-greedy and epsilon-decay strategies for optimal action selection. Tackle the Multi-Armed Bandit Problem, applying strategies to solve decision-making challenges under uncertainty.

Initializing

Exercicio

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

Instruções

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.