Implementar la regla de actualización SARSA

SARSA es un algoritmo on-policy en RL que actualiza la función valor-acción en función de la acción realizada y de la acción elegida en el siguiente estado. Este método ayuda a aprender el valor no solo del par estado-acción actual, sino también del siguiente, lo que permite aprender políticas que tienen en cuenta acciones futuras. Abajo tienes la regla de actualización de SARSA; tu tarea es implementar una función que actualice una Q-table siguiendo dicha regla.

La biblioteca NumPy ya se ha importado como np.

Image showing the mathematical formula of the SARSA update rule.

Este ejercicio forma parte del curso

Reinforcement Learning con Gymnasium en Python

Instrucciones del ejercicio

Recupera el valor Q actual para el par estado-acción indicado.
Busca el valor Q para el siguiente par estado-acción.
Actualiza el valor Q del par estado-acción actual usando la fórmula de SARSA.
Actualiza la Q-table Q, dado que un agente realiza la acción 0 en el estado 0, recibe una recompensa de 5, pasa al estado 1 y ejecuta la acción 1.

Ejercicio interactivo práctico

Prueba este ejercicio y completa el código de muestra.

def update_q_table(state, action, reward, next_state, next_action):
  	# Get the old value of the current state-action pair
    old_value = ____
    # Get the value of the next state-action pair
    next_value = ____
    # Compute the new value of the current state-action pair
    Q[(state, action)] = ____

alpha = 0.1
gamma  = 0.8
Q = np.array([[10,0],[0,20]], dtype='float32')
# Update the Q-table for the ('state1', 'action1') pair
____
print(Q)

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: Métodos Monte Carlo Exercise 2: Generación de episodios para métodos Monte Carlo Exercise 3: Implementar Monte Carlo de primera visita Exercise 4: Implementación de Monte Carlo de todas las visitas Exercise 5: Aprendizaje por diferencia temporal Exercise 6: Implementar la regla de actualización SARSA

Ejercicio actual

Exercise 7: Resolver Frozen Lake 8x8 con SARSA Exercise 8: Q-learning Exercise 9: Implementar la regla de actualización de Q-learning Exercise 10: Resolver Frozen Lake 8x8 con Q-learning Exercise 11: Evaluar la política en un Frozen Lake resbaladizo

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: Expected SARSA Exercise 2: Expected SARSA update rule Exercise 3: Applying Expected SARSA Exercise 4: Double Q-learning Exercise 5: Implementing double Q-learning update rule Exercise 6: Applying double Q-learning Exercise 7: Balancing exploration and exploitation Exercise 8: Defining epsilon-greedy function Exercise 9: Solving CliffWalking with epsilon greedy strategy Exercise 10: Solving CliffWalking with decayed epsilon-greedy strategy Exercise 11: Multi-armed bandits Exercise 12: Creating a multi-armed bandit Exercise 13: Solving a multi-armed bandit Exercise 14: Assessing convergence in a multi-armed bandit Exercise 15: Congratulations!