Dummy

Ver. 1.2.0 (2022-11-07)

This module provide Policy Dummy for unittest purpose.

class mlpro.rl.pool.policies.dummy.MyDummyPolicy(p_observation_space: MSpace, p_action_space: MSpace, p_buffer_size, p_batch_size=5, p_warm_up_step=10, p_ada: bool = True, p_visualize: bool = False, p_logging=True)

Bases: Policy

Creates a policy that satisfies mlpro interface.

Parameters:

p_observation_space (MSpace) – Subspace of an environment that is observed by the policy.

p_action_spaceMSpace

Action space object.

p_buffer_sizeint

Size of internal buffer. Default = 1.

p_batch_sizeint

Batch size. Default = 5

p_warm_up_stepint

Warm up step. Default = 10.

p_adabool

Boolean switch for adaptivity. Default = True.

p_visualizebool

Boolean switch for env/agent visualisation. Default = False.

p_logging

Log level (see constants of class Log). Default = Log.C_LOG_ALL.

C_NAME = 'MyPolicy'

C_BUFFER_CLS

alias of RandomSARSBuffer

add_buffer(p_buffer_element: SARSElement)

Intended to save the data to the buffer. By default it save the SARS data.

_add_additional_buffer(p_buffer_element: SARSElement)

clear_buffer()

Clears internal buffer (if buffering is active).

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_sars_elem: SARSElement) → 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