Een beleid verbeteren

In de vorige oefening heb je de Q-waarden berekend voor elk toestand-actie-paar in de MyGridWorld-omgeving. Nu ga je deze Q-waarden gebruiken om het bestaande beleid te verbeteren. Beleidsverbetering is een cruciale stap in reinforcement learning, waarbij je het beleid verbetert door acties te kiezen die in elke toestand de verwachte opbrengst (Q-waarde) maximaliseren. Na het verbeteren van het beleid render je de nieuwe bewegingen volgens dit verbeterde beleid.

De omgeving is geïmporteerd als env, samen met de Q-waarden als Q, en de functie render().

Deze oefening maakt deel uit van de cursus

Reinforcement Learning met Gymnasium in Python

Cursus bekijken

Oefeninstructies

Zoek de beste actie voor elke toestand op basis van Q-waarden.
Selecteer de juiste action op basis van de improved_policy.
Voer de geselecteerde action uit om het resultaat te bekijken.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

improved_policy = {}

for state in range(num_states-1):
    # Find the best action for each state based on Q-values
    max_action = ____
    improved_policy[state] = max_action

terminated = False
while not terminated:
  # Select action based on policy 
  action = ____
  # Execute the action
  state, reward, terminated, truncated, info = ____
  render()

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-beslissingsprocessen Exercise 2: Aangepaste Frozen Lake-MDP-componenten Exercise 3: Verkennen van toestand- en actieruimtes Exercise 4: Overgangswaarschijnlijkheden en beloningen Exercise 5: Policies en toestandswaardefuncties Exercise 6: Een deterministisch beleid definiëren Exercise 7: Toestandwaardes voor een policy berekenen Exercise 8: Beleid vergelijken Exercise 9: Actiewaardefuncties Exercise 10: Q-waarden berekenen Exercise 11: Een beleid verbeteren

Huidige oefening

Exercise 12: Policy-iteratie en value-iteratie Exercise 13: Policy-iteratie toepassen voor een optimale policy Exercise 14: Value-iteratie implementeren

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 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!