Menyelesaikan CliffWalking dengan strategi epsilon-greedy tereduksi

Untuk menyempurnakan strategi epsilon-greedy, sebuah faktor reduksi (decay) diperkenalkan untuk secara bertahap menurunkan laju eksplorasi, epsilon, seiring agen mempelajari lebih banyak tentang lingkungan. Pendekatan ini mendorong eksplorasi pada tahap awal pembelajaran dan pemanfaatan pengetahuan yang telah dipelajari ketika agen semakin akrab dengan lingkungan. Sekarang, Anda akan menerapkan strategi ini untuk menyelesaikan lingkungan CliffWalking.

Lingkungan telah diinisialisasi dan dapat diakses melalui variabel env. Variabel epsilon, min_epsilon, dan epsilon_decay telah didefinisikan untuk Anda. Fungsi epsilon_greedy() dan update_q_table() telah diimpor.

Latihan ini adalah bagian dari kursus

Reinforcement Learning dengan Gymnasium di Python

Petunjuk latihan

Implementasikan loop pelatihan penuh dengan memilih action, mengeksekusinya, menambahkan reward yang diterima ke episode_reward, dan memperbarui Q-table.
Kurangi epsilon menggunakan laju epsilon_decay, pastikan nilainya tidak turun di bawah min_epsilon.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

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))

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Reinforcement Learning dengan Gymnasium di Python

SkillTag.level.advancedSkillTag.label

4.8+

Mulai Kursus 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: Aturan pembaruan Expected SARSA Exercise 3: Menerapkan Expected SARSA Exercise 4: Double Q-learning Exercise 5: Menerapkan aturan pembaruan Double Q-learning Exercise 6: Menerapkan Double Q-learning Exercise 7: Menyeimbangkan eksplorasi dan eksploitasi Exercise 8: Mendefinisikan fungsi epsilon-greedy Exercise 9: Menyelesaikan CliffWalking dengan strategi epsilon-greedy Exercise 10: Menyelesaikan CliffWalking dengan strategi epsilon-greedy tereduksi

Latihan Saat Ini

Exercise 11: Multi-armed bandits Exercise 12: Membuat multi-armed bandit Exercise 13: Menyelesaikan multi-armed bandit Exercise 14: Menilai konvergensi pada multi-armed bandit Exercise 15: Selamat!