package emote.nn
Functions
def ortho_init_(m, gain) -> None
Classes
class ActionValueMlp(nn.Module):
Methods
def __init__(self, observation_dim, action_dim, hidden_dims) -> None
def forward(self, action, obs) -> Tensor
class GaussianMlpPolicy(nn.Module):
Methods
def __init__(self, observation_dim, action_dim, hidden_dims) -> None
def forward(self, obs, epsilon) -> Tensor | Tuple[Tensor]
class GaussianPolicyHead(nn.Module):
Methods
def __init__(self, hidden_dim, action_dim) -> None
def forward(self, x, epsilon) -> Tensor | Tuple[Tensor]
Sample pre-actions and associated log-probabilities.
Arguments:
x(Tensor)epsilon(Tensor | None)
Returns:
- Direct samples (pre-actions) from the policy log- probabilities associated to those samples