Assessing convergence in a multi-armed bandit

Evaluating the performance and convergence of strategies in a multi-armed bandit problem is crucial for understanding their effectiveness. By analyzing how frequently each arm is selected over time, we can infer the learning process and the strategy's ability to identify and exploit the best arm. This exercise involves visualizing the selection percentages of each arm over iterations to assess the convergence of an epsilon-greedy strategy.

The selected_arms array that shows which arm has been pulled in each iteration has been pre-loaded for you.

This exercise is part of the course

Reinforcement Learning with Gymnasium in Python

Exercise instructions

Initialize an array selections_percentage with zeros, with dimensions to track the selection percentage of each bandit over time.
Get the selections_percentage over time by calculating the cumulative sum of selections for each bandit over iterations, and dividing by the iteration number.
Plot the cumulative selection percentages for each bandit, to visualize how often each bandit is chosen over iterations.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Initialize the selection percentages with zeros
selections_percentage = ____
for i in range(n_iterations):
    selections_percentage[i, selected_arms[i]] = 1
# Compute the cumulative selection percentages 
selections_percentage = np.____(____, axis=____) / np.arange(1, ____).reshape(-1, 1)
for arm in range(n_bandits):
  	# Plot the cumulative selection percentage for each arm
    plt.plot(____, label=f'Bandit #{arm+1}')
plt.xlabel('Iteration Number')
plt.ylabel('Percentage of Bandit Selections (%)')
plt.legend()
plt.show()
for i, prob in enumerate(true_bandit_probs, 1):
    print(f"Bandit #{i} -> {prob:.2f}")

Edit and Run Code

This exercise is part of the course

Reinforcement Learning with Gymnasium in Python

AdvancedSkill Level

4.8+

Start Course for Free

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 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

Current Exercise

Exercise 15: Congratulations!