BaseStorage

source

BaseStorage(
   observation_space: gym.Space, action_space: gym.Space, device: str,
   storage_size: int, batch_size: int, num_envs: int
)

---

Base class of the storage module.

Args

• observation_space (gym.Space) : The observation space of environment.
• action_space (gym.Space) : The action space of environment.
• device (str) : Device (cpu, cuda, ...) on which the code should be run.
• storage_size (int) : The size of the storage.
• batch_size (int) : Batch size of samples.
• num_envs (int) : The number of parallel environments.

Returns

Instance of the base storage.

Methods:

.to_torch

source

.to_torch(
   x: np.ndarray
)

---

Convert numpy array to torch tensor.

Args

• x (np.ndarray) : Numpy array.

Returns

Torch tensor.

.reset

source

.reset()

---

Reset the storage.

.add

source

.add(
   *args, **kwargs
)

---

Add samples to the storage.

.sample

source

.sample(
   *args, **kwargs
)

---

Sample from the storage.

.update

source

.update(
   *args, **kwargs
)

---

Update the storage if necessary.