ray.rllib.utils.schedules.exponential_schedule.ExponentialSchedule#

class ray.rllib.utils.schedules.exponential_schedule.ExponentialSchedule(schedule_timesteps: int, framework: Optional[str] = None, initial_p: float = 1.0, decay_rate: float = 0.1)[source]#

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

Exponential decay schedule from initial_p to final_p.

Reduces output over schedule_timesteps. After this many time steps always returns final_p.

Methods

__init__(schedule_timesteps[, framework, ...])

Initializes a ExponentialSchedule instance.

value(t)

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