CliffWalking oplossen met een afnemende epsilon-greedystrategie

Als verbetering van de epsilon-greedystrategie wordt een vervalfactor geïntroduceerd om het exploratieniveau, epsilon, geleidelijk te verlagen naarmate de agent meer leert over de omgeving. Deze aanpak stimuleert in het begin vooral exploratie en later, wanneer de agent vertrouwd raakt met de omgeving, juist exploitatie van de geleerde kennis. Je gaat deze strategie nu toepassen om de CliffWalking-omgeving op te lossen.

De omgeving is geïnitialiseerd en is beschikbaar via de variabele env. De variabelen epsilon, min_epsilon en epsilon_decay zijn al voor je gedefinieerd. De functies epsilon_greedy() en update_q_table() zijn geïmporteerd.

Deze oefening maakt deel uit van de cursus

Reinforcement Learning met Gymnasium in Python

Cursus bekijken

Oefeninstructies

Implementeer de volledige trainingslus door een action te kiezen, die uit te voeren, de ontvangen reward op te tellen bij episode_reward, en de Q-tabel bij te werken.
Verlaag epsilon met de epsilon_decay-rate en zorg dat het niet onder min_epsilon komt.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

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))

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: 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: Expected SARSA Exercise 2: Expected SARSA-update-regel Exercise 3: Expected SARSA toepassen Exercise 4: Double Q-learning Exercise 5: Update-regel van Double Q-learning implementeren Exercise 6: Double Q-learning toepassen Exercise 7: Balans tussen exploratie en exploitatie Exercise 8: Epsilon-greedy-functie definiëren Exercise 9: CliffWalking oplossen met de epsilon-greedystrategie Exercise 10: CliffWalking oplossen met een afnemende epsilon-greedystrategie

Huidige oefening

Exercise 11: Multi-armed bandits Exercise 12: Een multi-armed bandit maken Exercise 13: Een multi-armed bandit oplossen Exercise 14: Convergentie beoordelen in een multi-armed bandit Exercise 15: Gefeliciteerd!