Random Actions

Ver. 1.0.5 (2023-09-21)

This module provides random genarator for multi purposes, e.g. testing environment, etc..

class mlpro.rl.pool.policies.randomgenerator.RandomGenerator(p_observation_space: MSpace, p_action_space: MSpace, p_id=None, p_buffer_size: int = 1, p_ada: bool = True, p_visualize: bool = False, p_logging=True)

Bases: Policy

A random policy that generates random actions for each dimension of the underlying action space.

See class mlpro.rl.Policy for further details.

C_NAME = 'RandomGenerator'

compute_action(p_state: State) → Action

Specific action computation method to be redefined.

Parameters:

p_obs (State) – Observation data.

Returns:

action – Action object.

Return type:

Action

_adapt(**p_kwargs) → bool

Adapts the policy based on State-Action-Reward-State (SARS) data.

Parameters:

p_sars_elem (SARSElement) – Object of type SARSElement.

Returns:

adapted – True, if something has been adapted. False otherwise.

Return type:

bool