Language Language English 简体中文

unilab.algos.torch.him_ppo.storage.HIMRolloutStorage

class unilab.algos.torch.him_ppo.storage.HIMRolloutStorage

Bases: object

Parameters:

• num_envs (int)

• num_transitions_per_env (int)

• obs_shape (Sequence[int])

• privileged_obs_shape (Sequence[int | None])

• actions_shape (Sequence[int])

• device (str)

Methods

__init__(num_envs, num_transitions_per_env, ...)
add_transition(transition)
add_transitions(transition)
clear()
compute_returns(last_values, gamma, lam)
mini_batch_generator(num_mini_batches[, ...])

class Transition

Bases: object

__init__()

clear()

Return type:

None

__init__(num_envs, num_transitions_per_env, obs_shape, privileged_obs_shape, actions_shape, device='cpu')

Parameters:

• num_envs (int)

• num_transitions_per_env (int)

• obs_shape (Sequence[int])

• privileged_obs_shape (Sequence[int | None])

• actions_shape (Sequence[int])

• device (str)

add_transition(transition)

Parameters:

transition (Transition)

Return type:

None

add_transitions(transition)

Parameters:

transition (Transition)

Return type:

None

clear()

Return type:

None

compute_returns(last_values, gamma, lam)

Parameters:

• last_values (Tensor)

• gamma (float)

• lam (float)

Return type:

None

mini_batch_generator(num_mini_batches, num_epochs=8)

Parameters:

• num_mini_batches (int)

• num_epochs (int)