memorax.algorithms.PQNConfig

class memorax.algorithms.PQNConfig

Bases: object

PQNConfig(num_envs: int, num_steps: int, gamma: float, td_lambda: float, num_minibatches: int, update_epochs: int, burn_in_length: int = 0)

num_envs: int

num_steps: int

gamma: float

td_lambda: float

num_minibatches: int

update_epochs: int

burn_in_length: int = 0

property batch_size

__init__(num_envs, num_steps, gamma, td_lambda, num_minibatches, update_epochs, burn_in_length=0)

Parameters:

• num_envs (int)

• num_steps (int)

• gamma (float)

• td_lambda (float)

• num_minibatches (int)

• update_epochs (int)

• burn_in_length (int)

Return type:

None

replace(**updates)

Returns a new object replacing the specified fields with new values.