* Minimum reward when success is now 0.1 * Fixed minimum reward when success
@@ -790,7 +790,7 @@ class MiniGridEnv(gym.Env):
Compute the reward to be given upon success
"""
- return 1 - 0.5 * (self.step_count / self.max_steps)
+ return 1 - 0.9 * (self.step_count / self.max_steps)
def _rand_int(self, low, high):