Campionare dal buffer PER

Prima di poter usare la classe Prioritized Experience Buffer per addestrare il tuo agente, devi ancora implementare il metodo .sample(). Questo metodo prende come argomento la dimensione del campione che vuoi estrarre e restituisce le transizioni campionate come tensors, insieme ai loro indici nel buffer di memoria e ai relativi pesi d'importanza.

Un buffer con capacità 10 è già stato caricato nel tuo ambiente per consentirti di effettuare i campionamenti.

Questo esercizio fa parte del corso

Deep Reinforcement Learning in Python

Visualizza il corso

Istruzioni dell'esercizio

Calcola la probabilità di campionamento associata a ciascuna transizione.
Estrai gli indici corrispondenti alle transizioni nel campione; np.random.choice(a, s, p=p) estrae un campione di dimensione s con reimmissione dall'array a, basandosi sull'array di probabilità p.
Calcola il peso d'importanza associato a ciascuna transizione.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

def sample(self, batch_size):
    priorities = np.array(self.priorities)
    # Calculate the sampling probabilities
    probabilities = ____ / np.sum(____)
    # Draw the indices for the sample
    indices = np.random.choice(____)
    # Calculate the importance weights
    weights = (1 / (len(self.memory) * ____)) ** ____
    weights /= np.max(weights)
    states, actions, rewards, next_states, dones = zip(*[self.memory[idx] for idx in indices])
    weights = [weights[idx] for idx in indices]
    states_tensor = torch.tensor(states, dtype=torch.float32)
    rewards_tensor = torch.tensor(rewards, dtype=torch.float32)
    next_states_tensor = torch.tensor(next_states, dtype=torch.float32)
    dones_tensor = torch.tensor(dones, dtype=torch.float32)
    weights_tensor = torch.tensor(weights, dtype=torch.float32)
    actions_tensor = torch.tensor(actions, dtype=torch.long).unsqueeze(1)
    return (states_tensor, actions_tensor, rewards_tensor, next_states_tensor,
            dones_tensor, indices, weights_tensor)

PrioritizedReplayBuffer.sample = sample
print("Sampled transitions:\n", buffer.sample(3))

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Deep Reinforcement Learning in Python

AvançadoNível de habilidade

4.8+

Inizia il corso gratis

Discover how deep reinforcement learning improves upon traditional Reinforcement Learning while studying and implementing your first Deep Q Learning algorithm.

Exercise 1: Introduction to deep reinforcement learning Exercise 2: Environment and neural network setup Exercise 3: DRL training loop Exercise 4: Introduction to deep Q learning Exercise 5: Deep learning and DQN Exercise 6: The Q-Network architecture Exercise 7: Instantiating the Q-Network Exercise 8: The barebone DQN algorithm Exercise 9: Barebone DQN action selection Exercise 10: Barebone DQN loss function Exercise 11: Training the barebone DQN

Dive into Deep Q-learning by implementing the original DQN algorithm, featuring Experience Replay, epsilon-greediness and fixed Q-targets. Beyond DQN, you will then explore two fascinating extensions that improve the performance and stability of Deep Q-learning: Double DQN and Prioritized Experience Replay.

Exercise 1: DQN con experience replay Exercise 2: La coda a due estremità Exercise 3: Experience replay buffer Exercise 4: DQN con experience replay Exercise 5: L'algoritmo DQN completo Exercise 6: Epsilon-greediness Exercise 7: Q-target fissi Exercise 8: Implementare l'algoritmo DQN completo Exercise 9: Double DQN Exercise 10: Rete online e rete target in DDQN Exercise 11: Addestrare il Double DQN Exercise 12: Prioritized experience replay Exercise 13: Prioritized experience replay buffer Exercise 14: Campionare dal buffer PER

Esercizio in corso

Exercise 15: DQN con prioritized experience replay

Learn about the foundational concepts of policy gradient methods found in DRL. You will begin with the policy gradient theorem, which forms the basis for these methods. Then, you will implement the REINFORCE algorithm, a powerful approach to learning policies. The chapter will then guide you through Actor-Critic methods, focusing on the Advantage Actor-Critic (A2C) algorithm, which combines the strengths of both policy gradient and value-based methods to enhance learning efficiency and stability.

Exercise 1: Introduction to policy gradient Exercise 2: The policy network architecture Exercise 3: Working with discrete distributions Exercise 4: Policy gradient and REINFORCE Exercise 5: Action selection in REINFORCE Exercise 6: Training the REINFORCE algorithm Exercise 7: Advantage Actor Critic Exercise 8: Critic network Exercise 9: Actor Critic loss calculations Exercise 10: Training the A2C algorithm

Explore Proximal Policy Optimization (PPO) for robust DRL performance. Next, you will examine using an entropy bonus in PPO, which encourages exploration by preventing premature convergence to deterministic policies. You'll also learn about batch updates in policy gradient methods. Finally, you will learn about hyperparameter optimization with Optuna, a powerful tool for optimizing performance in your DRL models.

Exercise 1: Proximal policy optimization Exercise 2: The clipped probability ratio Exercise 3: The clipped surrogate objective function Exercise 4: Entropy bonus and PPO Exercise 5: Entropy playground Exercise 6: Training the PPO algorithm Exercise 7: Batch updates in policy gradient Exercise 8: Minibatch and DRL Exercise 9: A2C with batch updates Exercise 10: Hyperparameter optimization with Optuna Exercise 11: Hyperparameter or not?Exercise 12: Hands-on with Optuna Exercise 13: Congratulations!