def __init__(self):
BaseReward.__init__(self)
# required if you want to design a custom reward taking into account the
# alarm feature
self.has_alarm_component = True
self.is_alarm_used = False # required to update it in __call__ !!
self.total_time_steps = dt_float(0.0)
self.reward_min = dt_float(-1.)
self.reward_max = dt_float(1.)
self.reward_no_game_over = dt_float(0.)
self.window_size = None
self.best_time = None
self.mult_for_right_zone = 2
def __init__(self):
BaseReward.__init__(self)
self.reward_min = None
self.reward_max = None
self.worst_cost = None
def __init__(self, *args, **kwargs):
BaseReward.__init__(self, *args, **kwargs)
warnings.warn(
"Reward class has been renamed \"BaseReward\". "
"This class Action will be removed in future versions.",
category=PendingDeprecationWarning)
def __init__(self, alpha_redisph=1.0):
BaseReward.__init__(self)
self.reward_min = dt_float(1.0) # carefull here between min and max...
self.reward_max = dt_float(300.0 * 70.0)
self.alpha_redisph = dt_float(alpha_redisph)
def __init__(self):
BaseReward.__init__(self)
self.reward_min = dt_float(0.0)
self.reward_max = dt_float(1.0)
self.penalty_max_at_n_lines = dt_float(2.0)
def __init__(self, per_timestep=1):
BaseReward.__init__(self)
self.per_timestep = dt_float(per_timestep)
self.reward_min = dt_float(0.0)
def __init__(self):
BaseReward.__init__(self)
def __init__(self, per_timestep=1):
BaseReward.__init__(self)
self.per_timestep = per_timestep
self.total_reward = 0
self.reward_min = 0
self.reward_max = per_timestep
def __init__(self):
BaseReward.__init__(self)
self.reward_min = None
self.reward_max = None
self.max_regret = dt_float(0.0)
self.reward_illegal_ambiguous = None
def __init__(self):
BaseReward.__init__(self)
self.reward_min = -1000.0
self.reward_max = 1000.0
self.penalty_per_diff = -500.0
def __init__(self, min_pen_lte=0.0, max_pen_gte=1.0):
BaseReward.__init__(self)
self.reward_min = dt_float(0.0)
self.reward_max = dt_float(1.0)
self.min_pen_lte = dt_float(min_pen_lte)
self.max_pen_gte = dt_float(max_pen_gte)
def __init__(self):
BaseReward.__init__(self)
self.reward_min = 0
self.reward_max = 0
self.rewards = {}
def __init__(self, alpha_redisph=5.0):
BaseReward.__init__(self)
self.reward_min = None
self.reward_max = None
self.max_regret = 0.
self.alpha_redisph = alpha_redisph
def __init__(self, per_timestep=1):
BaseReward.__init__(self)
self.per_timestep = dt_float(per_timestep)
self.total_time_steps = dt_float(0.0)
self.reward_min = dt_float(0.)
self.reward_max = dt_float(1.)
def __init__(self):
BaseReward.__init__(self)
self.reward_min = -1000.0
self.reward_max = 1000.0
def __init__(self):
BaseReward.__init__(self)
self.reward_min = dt_float(0.0)
self.reward_max = dt_float(1.0)
self.worst_cost = None
def __init__(self):
BaseReward.__init__(self)
self.reward_min = dt_float(0.0)
self.reward_max = dt_float(1.0)
self.max_overflowed = dt_float(5.0)
def __init__(self):
BaseReward.__init__(self)
self.reward_min = dt_float(-1.0)
self.reward_max = dt_float(1.0)
def __init__(self, max_lines=5):
BaseReward.__init__(self)
self.reward_min = dt_float(0.0)
self.reward_max = dt_float(1.0)
self.max_overflowed = dt_float(max_lines)
def __init__(self, alpha_redisph=5.0):
BaseReward.__init__(self)
self.reward_min = None
self.reward_max = None
self.max_regret = dt_float(0.0)
self.alpha_redisph = dt_float(alpha_redisph)
def __init__(self):
BaseReward.__init__(self)
self.reward_min = -1.0
self.reward_illegal = -0.5
self.reward_max = 1.0