Ejemplo n.º 1
0
 def compute_reward(self, state, rl_actions, **kwargs):
     return rewards.penalize_tl_changes(rl_actions >= 0.5, gain=1.0)
Ejemplo n.º 2
0
 def compute_reward(self, state, rl_actions, **kwargs):
     """See class definition."""
     return rewards.penalize_tl_changes(rl_actions >= 0.5, gain=1.0)