rlgt.agents.random_action_mechanisms.ConstantRandomActionMechanism

class documentation

class ConstantRandomActionMechanism(RandomActionMechanism):

Constructor: ConstantRandomActionMechanism(random_action_probability)

View In Hierarchy

This class inherits from the RandomActionMechanism class and represents a random action mechanism in which the probability of executing a random action is constant and specified at construction time.

Method __init__ This constructor initializes the random action mechanism with a fixed random action probability.
Method reset This abstract method must be implemented by any concrete subclass. It is invoked by an RL agent during the initialization process and it must initialize or reset all internal state maintained by the random action mechanism.
Method step This abstract method must be implemented by any concrete subclass. It is invoked by an RL agent at the end of each iteration of the learning process and it must update the internal state of the random action mechanism based on the previous best score and the current best score.
Property random_action_probability This abstract property must be implemented by any concrete subclass. It must return the current random action probability as a float value from the interval [0, 1].
Instance Variable __random_action_probability A float from the interval [0, 1] that determines the constant probability with which a random action is executed.
def __init__(self, random_action_probability: float):

This constructor initializes the random action mechanism with a fixed random action probability.

Parameters
random_action_probability:floatThe constant probability of executing a random action, given as a float from the interval [0, 1].
def reset(self):
overrides rlgt.agents.random_action_mechanisms.RandomActionMechanism.reset

This abstract method must be implemented by any concrete subclass. It is invoked by an RL agent during the initialization process and it must initialize or reset all internal state maintained by the random action mechanism.

def step(self, previous_best_score: float, current_best_score: float):
overrides rlgt.agents.random_action_mechanisms.RandomActionMechanism.step

This abstract method must be implemented by any concrete subclass. It is invoked by an RL agent at the end of each iteration of the learning process and it must update the internal state of the random action mechanism based on the previous best score and the current best score.

Parameters
previous_best_score:floatThe value of the best score before the current iteration, given as a float.
current_best_score:floatThe value of the best score after the current iteration, given as a float.
random_action_probability: float =
overrides rlgt.agents.random_action_mechanisms.RandomActionMechanism.random_action_probability

This abstract property must be implemented by any concrete subclass. It must return the current random action probability as a float value from the interval [0, 1].

__random_action_probability: float =

A float from the interval [0, 1] that determines the constant probability with which a random action is executed.