De SARSA-update regel implementeren

SARSA is een on-policy algoritme in RL dat de actie-waardefunctie bijwerkt op basis van de uitgevoerde actie en de in de volgende toestand gekozen actie. Deze methode helpt niet alleen de waarde van het huidige toestand-actie-paar te leren, maar ook van het daaropvolgende paar, zodat je beleid kunt leren dat rekening houdt met toekomstige acties. Hieronder staat de SARSA-update regel, en jouw taak is een functie te implementeren die een Q-tabel bijwerkt op basis van deze regel.

De NumPy-bibliotheek is voor je geïmporteerd als np.

Image showing the mathematical formula of the SARSA update rule.

Deze oefening maakt deel uit van de cursus

Reinforcement Learning met Gymnasium in Python

Cursus bekijken

Oefeninstructies

Haal de huidige Q-waarde op voor het gegeven toestand-actie-paar.
Zoek de Q-waarde voor het volgende toestand-actie-paar.
Werk de Q-waarde voor het huidige toestand-actie-paar bij met de SARSA-formule.
Werk de Q-tabel Q bij, gegeven dat een agent actie 0 uitvoert in toestand 0, een beloning van 5 ontvangt, naar toestand 1 gaat en actie 1 uitvoert.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

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)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Reinforcement Learning met Gymnasium in Python

SkillTag.level.advancedSkillTag.label

4.8+

Begin de cursus 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: Montecarlo-methoden Exercise 2: Episodes genereren voor Monte Carlo-methoden Exercise 3: First-visit Monte Carlo implementeren Exercise 4: Every-Visit Monte Carlo implementeren Exercise 5: Temporal-differentieleren Exercise 6: De SARSA-update regel implementeren

Huidige oefening

Exercise 7: 8x8 Frozen Lake oplossen met SARSA Exercise 8: Q-learning Exercise 9: Q-learning-bijwerkregel implementeren Exercise 10: 8x8 Frozen Lake oplossen met Q-learning Exercise 11: Beleid evalueren op een glad 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: 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!