Resolver CliffWalking con una estrategia epsilon-greedy decreciente

Para mejorar la estrategia epsilon-greedy, introducimos un factor de decaimiento para reducir gradualmente la tasa de exploración, epsilon, a medida que el agente aprende más sobre el entorno. Este enfoque fomenta la exploración en las primeras fases del aprendizaje y la explotación del conocimiento adquirido cuando el agente se familiariza con el entorno. Ahora, aplicarás esta estrategia para resolver el entorno CliffWalking.

El entorno ya está inicializado y puedes acceder a él mediante la variable env. Las variables epsilon, min_epsilon y epsilon_decay están predefinidas. Las funciones epsilon_greedy() y update_q_table() ya se han importado.

Este ejercicio forma parte del curso

Reinforcement Learning con Gymnasium en Python

Instrucciones del ejercicio

Implementa el bucle completo de entrenamiento eligiendo una action, ejecutándola, acumulando la reward recibida en episode_reward y actualizando la Q-table.
Disminuye epsilon usando la tasa epsilon_decay, asegurándote de que no baje de min_epsilon.

Ejercicio interactivo práctico

Prueba este ejercicio y completa el código de muestra.

rewards_decay_eps_greedy = []
for episode in range(total_episodes):
    state, info = env.reset()
    episode_reward = 0
    for i in range(max_steps):
      	# Implement the training loop
        action = ____
        new_state, reward, terminated, truncated, info = ____
        episode_reward += ____       
        ____      
        state = new_state
    rewards_decay_eps_greedy.append(episode_reward)
    # Update epsilon
    epsilon = ____
print("Average reward per episode: ", np.mean(rewards_decay_eps_greedy))

Editar y ejecutar código

Este ejercicio forma parte del curso

Reinforcement Learning con Gymnasium en Python

AvanzadoNivel de habilidad

4.8+

Comienza el curso gratis

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.

Exercise 1: Fundamentals of reinforcement learning Exercise 2: What is Reinforcement Learning?Exercise 3: RL vs. other ML sub-domains Exercise 4: Scenarios for applying RL Exercise 5: Navigating the RL framework Exercise 6: RL interaction loop Exercise 7: Episodic and continuous RL tasks Exercise 8: Calculating discounted returns for agent strategies Exercise 9: Interacting with Gymnasium environments Exercise 10: Setting up a Mountain Car environment Exercise 11: Visualizing the Mountain Car Environment Exercise 12: Interacting with the Frozen Lake environment

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.

Exercise 1: Markov Decision Processes Exercise 2: Custom Frozen Lake MDP components Exercise 3: Exploring state and action spaces Exercise 4: Transition probabilities and rewards Exercise 5: Policies and state-value functions Exercise 6: Defining a deterministic policy Exercise 7: Computing state-values for a policy Exercise 8: Comparing policies Exercise 9: Action-value functions Exercise 10: Computing Q-values Exercise 11: Improving a policy Exercise 12: Policy iteration and value iteration Exercise 13: Applying policy iteration for optimal policy Exercise 14: Implementing value iteration

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.

Exercise 1: Monte Carlo methods Exercise 2: Episode generation for Monte Carlo methods Exercise 3: Implementing first-visit Monte Carlo Exercise 4: Implementing every-visit Monte Carlo Exercise 5: Temporal difference learning Exercise 6: Implementing the SARSA update rule Exercise 7: Solving 8x8 Frozen Lake with SARSA Exercise 8: Q-learning Exercise 9: Implementing Q-learning update rule Exercise 10: Solving 8x8 Frozen Lake with Q-learning Exercise 11: Evaluating policy on a slippery Frozen Lake

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.

Exercise 1: SARSA esperado Exercise 2: Regla de actualización de Expected SARSA Exercise 3: Aplicar Expected SARSA Exercise 4: Double Q-learning Exercise 5: Implementar la regla de actualización de Double Q-learning Exercise 6: Aplicar Double Q-learning Exercise 7: Equilibrar exploración y explotación Exercise 8: Definir la función epsilon-greedy Exercise 9: Resolver CliffWalking con la estrategia epsilon-greedy Exercise 10: Resolver CliffWalking con una estrategia epsilon-greedy decreciente

Ejercicio actual

Exercise 11: Bandidos de varios brazos Exercise 12: Creando un multi-armed bandit Exercise 13: Resolver un bandido de varios brazos Exercise 14: Evaluar la convergencia en un problema de multi-armed bandit Exercise 15: ¡Enhorabuena!