# Copyright (c) 2019-2020, RTE (https://www.rte-france.com)
# See AUTHORS.txt
# This Source Code Form is subject to the terms of the Mozilla Public License, version 2.0.
# If a copy of the Mozilla Public License, version 2.0 was not distributed with this file,
# you can obtain one at http://mozilla.org/MPL/2.0/.
# SPDX-License-Identifier: MPL-2.0
# This file is part of Grid2Op, Grid2Op a testbed platform to model sequential decision making in power systems.
import numpy as np
from grid2op.Reward.baseReward import BaseReward
from grid2op.dtypes import dt_float
[docs]class IncreasingFlatReward(BaseReward):
"""
This reward just counts the number of timestep the agent has successfully manage to perform.
It adds a constant reward for each time step successfully handled.
Examples
---------
You can use this reward in any environment with:
.. code-block:: python
import grid2op
from grid2op.Reward import IncreasingFlatReward
# then you create your environment with it:
NAME_OF_THE_ENVIRONMENT = "l2rpn_case14_sandbox"
env = grid2op.make(NAME_OF_THE_ENVIRONMENT,reward_class=IncreasingFlatReward)
# and do a step with a "do nothing" action
obs = env.reset()
obs, reward, done, info = env.step(env.action_space())
# the reward is computed with the IncreasingFlatReward class
"""
[docs] def __init__(self, per_timestep=1, logger=None):
BaseReward.__init__(self, logger=logger)
self.per_timestep = dt_float(per_timestep)
self.reward_min = dt_float(0.0)
[docs] def initialize(self, env):
if env.chronics_handler.max_timestep() > 0:
self.reward_max = env.chronics_handler.max_timestep() * self.per_timestep
else:
self.reward_max = np.inf
[docs] def __call__(self, action, env, has_error, is_done, is_illegal, is_ambiguous):
if not has_error:
res = dt_float(env.nb_time_step * self.per_timestep)
else:
res = self.reward_min
return res