ray.rllib.utils.schedules.piecewise_schedule.PiecewiseSchedule#

class ray.rllib.utils.schedules.piecewise_schedule.PiecewiseSchedule(endpoints: List[Tuple[int, float]], framework: Optional[str] = None, interpolation: Callable[[Union[numpy.array, jnp.ndarray, tf.Tensor, torch.Tensor], Union[numpy.array, jnp.ndarray, tf.Tensor, torch.Tensor], Union[numpy.array, jnp.ndarray, tf.Tensor, torch.Tensor]], Union[numpy.array, jnp.ndarray, tf.Tensor, torch.Tensor]] = <function _linear_interpolation>, outside_value: Optional[float] = None)[source]#

Bases: ray.rllib.utils.schedules.schedule.Schedule

Implements a Piecewise Scheduler.

Methods

__init__(endpoints[, framework, ...])

Initializes a PiecewiseSchedule instance.

value(t)

Generates the value given a timestep (based on schedule's logic).