reinforcement_learning.core
add_suffix(input_dict, suffix)
Add suffix to dict keys.
Source code in src/python/easydel/reinforcement_learning/core.py
92 93 94 |
|
multinomial(logits, num_samples, replacement=False)
Implements the torch.multinomial
function in JAX.
Args: logits (jnp.array): The unnormalized log probabilities of the events. num_samples (int): The number of samples to draw. replacement (bool): Don't use this ; Returns: jnp.array: A matrix of shape (num_samples, batch_size) containing the sampled indices.
Source code in src/python/easydel/reinforcement_learning/core.py
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 |
|