memorax.algorithms.PQNConfig

memorax.algorithms.PQNConfig#

class memorax.algorithms.PQNConfig[source]#

Bases: object

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

name: str#
num_envs: int#
num_eval_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__(name, num_envs, num_eval_envs, num_steps, gamma, td_lambda, num_minibatches, update_epochs, burn_in_length=0)#
Parameters:

  • name (str)

  • num_envs (int)

  • num_eval_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.

Contents