rofunc.learning.RofuncRL.utils.memory

1.  Module Contents

1.1.  Classes

Memory
RandomMemory

1.2.  API

class rofunc.learning.RofuncRL.utils.memory.Memory(memory_size: int, num_envs: int = 1, device: Optional[Union[str, torch.device]] = None, export: bool = False, export_format: str = 'pt', export_directory: str = '')

Initialization

Base class representing a memory with circular buffers

Buffers are torch tensors with shape (memory size, number of environments, data size). Circular buffers are implemented with two integers: a memory index and an environment index

Parameters:

• memory_size (int) – Maximum number of elements in the first dimension of each internal storage

• num_envs (int, optional) – Number of parallel environments (default: 1)

• device (str or torch.device, optional) – Device on which a torch tensor is or will be allocated (default: None). If None, the device will be either "cuda:0" if available or "cpu"

• export (bool, optional) – Export the memory to a file (default: False). If True, the memory will be exported when the memory is filled

• export_format (str, optional) – Export format (default: “pt”). Supported formats: torch (pt), numpy (np), comma separated values (csv)

• export_directory (str, optional) – Directory where the memory will be exported (default: “”). If empty, the agent’s experiment directory will be used

Raises:

ValueError – The export format is not supported

share_memory() → None

Share the tensors between processes

get_tensor_names() → Tuple[str]

Get the name of the internal tensors in alphabetical order

Returns:

Tensor names without internal prefix (_tensor_)

Return type:

tuple of strings

get_tensor_by_name(name: str, keepdim: bool = True) → torch.Tensor

Get a tensor by its name

Parameters:

• name (str) – Name of the tensor to retrieve

• keepdim (bool, optional) – Keep the tensor’s shape (memory size, number of environments, size) (default: True) If False, the returned tensor will have a shape of (memory size * number of environments, size)

Raises:

KeyError – The tensor does not exist

Returns:

Tensor

Return type:

torch.Tensor

set_tensor_by_name(name: str, tensor: Union[torch.Tensor, rofunc.learning.RofuncRL.processors.standard_scaler.RunningStandardScaler]) → None

Set a tensor by its name

Parameters:

• name (str) – Name of the tensor to set

• tensor (torch.Tensor) – Tensor to set

Raises:

KeyError – The tensor does not exist

create_tensor(name: str, size: Union[int, Tuple[int], gym.Space, gymnasium.Space], dtype: Optional[torch.dtype] = None, keep_dimensions: bool = False) → bool

Create a new internal tensor in memory The tensor will have a 3-components shape (memory size, number of environments, size). The internal representation will use _tensor_<name> as the name of the class property :param name: Tensor name (the name has to follow the python PEP 8 style) :param size: Number of elements in the last dimension (effective data size).

The product of the elements will be computed for sequences or gym/gymnasium spaces

Parameters:

• dtype – Data type (torch.dtype). If None, the global default torch data type will be used (default)

• keep_dimensions – Whether or not to keep the dimensions defined through the size parameter (default: False)

reset() → None

Reset the memory by cleaning internal indexes and flags

Old data will be retained until overwritten, but access through the available methods will not be guaranteed

Default values of the internal indexes and flags

• filled: False

• env_index: 0

• memory_index: 0

add_samples(**tensors: torch.Tensor) → None

Record samples in memory

Samples should be a tensor with 2-components shape (number of environments, data size). All tensors must be of the same shape

According to the number of environments, the following classification is made:

• one environment: Store a single sample (tensors with one dimension) and increment the environment index (second index) by one

• number of environments less than num_envs: Store the samples and increment the environment index (second index) by the number of the environments

• number of environments equals num_envs: Store the samples and increment the memory index (first index) by one

Parameters:

tensors (dict) – Sampled data as key-value arguments where the keys are the names of the tensors to be modified. Non-existing tensors will be skipped

Raises:

ValueError – No tensors were provided or the tensors have incompatible shapes

abstract sample(names: Union[Tuple[str], List[str]], batch_size: int, mini_batches: int = 1, sequence_length: int = 1) → List[List[torch.Tensor]]

Data sampling method to be implemented by the inheriting classes

Parameters:

• names (tuple or list of strings) – Tensors names from which to obtain the samples

• batch_size (int) – Number of element to sample

• mini_batches (int, optional) – Number of mini-batches to sample (default: 1)

• sequence_length (int, optional) – Length of each sequence (default: 1)

Raises:

NotImplementedError – The method has not been implemented

Returns:

Sampled data from tensors sorted according to their position in the list of names. The sampled tensors will have the following shape: (batch size, data size)

Return type:

list of torch.Tensor list

sample_by_index(names: Tuple[str], indexes: Union[tuple, numpy.ndarray, torch.Tensor], mini_batches: int = 1) → List[List[torch.Tensor]]

Sample data from memory according to their indexes

Parameters:

• names (tuple or list of strings) – Tensors names from which to obtain the samples

• indexes (tuple or list, numpy.ndarray or torch.Tensor) – Indexes used for sampling

• mini_batches (int, optional) – Number of mini-batches to sample (default: 1)

Returns:

Sampled data from tensors sorted according to their position in the list of names. The sampled tensors will have the following shape: (number of indexes, data size)

Return type:

list of torch.Tensor list

sample_all(names: List[str], mini_batches: int = 1, sequence_length: int = 1) → List[List[torch.Tensor]]

Sample all data from memory

Parameters:

• names (tuple or list of strings) – Tensors names from which to obtain the samples

• mini_batches (int, optional) – Number of mini-batches to sample (default: 1)

• sequence_length (int, optional) – Length of each sequence (default: 1)

Returns:

Sampled data from memory. The sampled tensors will have the following shape: (memory size * number of environments, data size)

Return type:

list of torch.Tensor list

get_sampling_indexes() → Union[tuple, numpy.ndarray, torch.Tensor]

Get the last indexes used for sampling

Returns:

Last sampling indexes

Return type:

tuple or list, numpy.ndarray or torch.Tensor

save(directory: str = '', format: str = 'pt') → None

Save the memory to a file

Supported formats:

• PyTorch (pt)

• NumPy (npz)

• Comma-separated values (csv)

Parameters:

• directory (str) – Path to the folder where the memory will be saved. If not provided, the directory defined in the constructor will be used

• format (str, optional) – Format of the file where the memory will be saved (default: “pt”)

Raises:

ValueError – If the format is not supported

load(path: str) → None

Load the memory from a file

Supported formats: - PyTorch (pt) - NumPy (npz) - Comma-separated values (csv)

Parameters:

path (str) – Path to the file where the memory will be loaded

Raises:

ValueError – If the format is not supported

class rofunc.learning.RofuncRL.utils.memory.RandomMemory(memory_size: int, num_envs: int = 1, device: Optional[Union[str, torch.device]] = None, export: bool = False, export_format: str = 'pt', export_directory: str = '', replacement=True)

Bases: rofunc.learning.RofuncRL.utils.memory.Memory

Initialization

Random sampling memory

Sample a batch from memory randomly

Parameters:

• memory_size (int) – Maximum number of elements in the first dimension of each internal storage

• num_envs (int, optional) – Number of parallel environments (default: 1)

• device (str or torch.device, optional) – Device on which a torch tensor is or will be allocated (default: None). If None, the device will be either "cuda:0" if available or "cpu"

• export (bool, optional) – Export the memory to a file (default: False). If True, the memory will be exported when the memory is filled

• export_format (str, optional) – Export format (default: “pt”). Supported formats: torch (pt), numpy (np), comma separated values (csv)

• export_directory (str, optional) – Directory where the memory will be exported (default: “”). If empty, the agent’s experiment directory will be used

• replacement (bool, optional) – Flag to indicate whether the sample is with or without replacement (default: True). Replacement implies that a value can be selected multiple times (the batch size is always guaranteed). Sampling without replacement will return a batch of maximum memory size if the memory size is less than the requested batch size

Raises:

ValueError – The export format is not supported

sample(names: Tuple[str], batch_size: int, mini_batches: int = 1, sequence_length: int = 1) → List[List[torch.Tensor]]

Sample a batch from memory randomly

Parameters:

• names (tuple or list of strings) – Tensors names from which to obtain the samples

• batch_size (int) – Number of element to sample

• mini_batches (int, optional) – Number of mini-batches to sample (default: 1)

• sequence_length (int, optional) – Length of each sequence (default: 1)

Returns:

Sampled data from tensors sorted according to their position in the list of names. The sampled tensors will have the following shape: (batch size, data size)

Return type:

list of torch.Tensor list