visualizers.viser_app.controllers.sampling.cmaes#

Module Contents#

class visualizers.viser_app.controllers.sampling.cmaes.CMAESConfig#

Bases: jacta.visualizers.viser_app.controllers.sampling_base.SamplingBaseConfig

Configuration for CMAES sampling. .. py:attribute:: sigma_init

type:

float

value:

0.05

max_iter: int = 20#
class visualizers.viser_app.controllers.sampling.cmaes.CMAES(task: jacta.visualizers.viser_app.tasks.task.Task, config: CMAESConfig, reward_config: jacta.visualizers.viser_app.tasks.task.TaskConfig)#

Bases: jacta.visualizers.viser_app.controllers.sampling_base.SamplingBase

CMAES planner.

Parameters:

  • config (CMAESConfig) – configuration object with hyperparameters for planner.

  • model – mujoco model of system being controlled.

  • data – current configuration data for mujoco model.

  • reward_func – function mapping batches of states/controls to batches of rewards.

  • task (jacta.visualizers.viser_app.tasks.task.Task) –

  • reward_config (jacta.visualizers.viser_app.tasks.task.TaskConfig) –

update_action(curr_state: numpy.ndarray, curr_time: float, additional_info: dict[str, Any]) → None#

Performs rollouts + reward computation from current state.

Parameters:

  • curr_state (numpy.ndarray) –

  • curr_time (float) –

  • additional_info (dict[str, Any]) –

Return type:

None

action(time: float) → numpy.ndarray#

Current best action of policy.

Parameters:

time (float) –

Return type:

numpy.ndarray