lstm

ray.rllib.utils.numpy.lstm(x, weights: ndarray, biases: ndarray | None = None, initial_internal_states: ndarray | None = None, time_major: bool = False, forget_bias: float = 1.0)

Calculates LSTM layer output given weights/biases, states, and input.

Parameters:

• x – The inputs to the LSTM layer including time-rank (0th if time-major, else 1st) and the batch-rank (1st if time-major, else 0th).

• weights (ndarray) – The weights matrix.

• biases (ndarray | None) – The biases vector. All 0s if None.

• initial_internal_states (ndarray | None) – The initial internal states to pass into the layer. All 0s if None.

• time_major (bool) – Whether to use time-major or not. Default: False.

• forget_bias (float) – Gets added to first sigmoid (forget gate) output. Default: 1.0.

Returns:

Tuple consisting of 1) The LSTM layer’s output and 2) Tuple: Last (c-state, h-state).