Struct relearn::torch::history::features::PackedHistoryFeatures [−][src]
pub struct PackedHistoryFeatures {
pub discount_factor: f64,
pub episode_ranges: Vec<Range<usize>>,
pub batch_sizes: Option<Vec<i64>>,
pub batch_sizes_tensor: Option<Tensor>,
pub observation_features: Option<Tensor>,
pub actions: Option<Tensor>,
pub returns: Option<Tensor>,
pub rewards: Option<Tensor>,
pub device: Device,
}
Expand description
Packed history features.
Panics
The PackedHistoryFeaturesView
this provides will panic
if the requested features is not available.
Fields
discount_factor: f64
episode_ranges: Vec<Range<usize>>
batch_sizes: Option<Vec<i64>>
batch_sizes_tensor: Option<Tensor>
observation_features: Option<Tensor>
actions: Option<Tensor>
returns: Option<Tensor>
rewards: Option<Tensor>
device: Device
Trait Implementations
Discount factor for calculating returns.
Episode index ranges sorted in decreasing order of episode length.
Batch sizes in the packing. A 1D i64 tensor.
Packed observation features. A 2D f64 tensor.
This method tests for self
and other
values to be equal, and is used
by ==
. Read more
This method tests for !=
.