sinergym.utils.callbacks.LoggerCallback
- class sinergym.utils.callbacks.LoggerCallback(sinergym_logger=False, verbose=0)
Custom callback for plotting additional values in tensorboard. :param ep_rewards: Here will be stored all rewards during episode. :param ep_powers: Here will be stored all consumption data during episode. :param ep_term_comfort: Here will be stored all comfort terms (reward component) during episode. :param ep_term_energy: Here will be stored all energy terms (reward component) during episode. :param num_comfort_violation: Number of timesteps in which comfort has been violated. :param ep_timesteps: Each timestep during an episode, this value increment 1.
- __init__(sinergym_logger=False, verbose=0)
Custom callback for plotting additional values in tensorboard. :param sinergym_logger: Indicate if CSVLogger inner Sinergym will be activated or not. :type sinergym_logger: boolean
Methods
__init__([sinergym_logger, verbose])Custom callback for plotting additional values in tensorboard.
init_callback(model)Initialize the callback by saving references to the RL model and the training environment for convenience.
on_rollout_end()on_rollout_start()on_step()This method will be called by the model after each call to
env.step().on_training_start(locals_, globals_)update_child_locals(locals_)Update the references to the local variables on sub callbacks.
update_locals(locals_)Update the references to the local variables.
- on_training_end()