fixing yet again some other tests

Signed-off-by: DONNOT Benjamin <[email protected]>

Author: BDonnot

grid2op/Environment/environment.py

@@ -980,6 +980,7 @@ def reset_grid(self,
             self._backend_action = self._backend_action_class()
 
         if self._init_obs is not None:
+            # NB this is called twice (once at the end of reset), this is the first call
             self._reset_to_orig_state(self._init_obs)
 
         init_action = None
@@ -1443,6 +1444,11 @@ def reset(self,
         self._observation_space.reset(self)
         self._observation_space.set_real_env_kwargs(self)
         self._called_from_reset = False        
+        
+        # reset cooldowns and all
+        if self._init_obs is not None:
+            # NB this is called twice (once in reset_grid), this is the second call
+            self._reset_to_orig_state(self._init_obs)
         # force the first observation to be generated properly
         self._last_obs = None
         return self.get_obs()

grid2op/tests/test_multi_steps_env.py

@@ -89,17 +89,17 @@ def test_cooldown(self):
         un_act = self.env.action_space({"set_line_status": [(5, +1)]})
         obs = self.env.reset()
         obs, *_ = self.env.step(act)
-        assert obs.time_before_cooldown_line[5] == 3
+        assert obs.time_before_cooldown_line[5] == 3, f"{obs.time_before_cooldown_line[5]} vs 3"
 
         forecast_env = obs.get_forecast_env()
         f_obs = forecast_env.reset()
-        assert f_obs.time_before_cooldown_line[5] == 3
+        assert f_obs.time_before_cooldown_line[5] == 3, f"{f_obs.time_before_cooldown_line[5]} vs 3"
         f_obs2, *_ = forecast_env.step(self.dn)
-        assert f_obs2.time_before_cooldown_line[5] == 2
+        assert f_obs2.time_before_cooldown_line[5] == 2, f"{f_obs2.time_before_cooldown_line[5]} vs 2"
         f_obs3, *_ = forecast_env.step(self.dn)
-        assert f_obs3.time_before_cooldown_line[5] == 1
+        assert f_obs3.time_before_cooldown_line[5] == 1, f"{f_obs3.time_before_cooldown_line[5]} vs 1"
         f_obs4, r, done, info = forecast_env.step(un_act)
-        assert f_obs4.time_before_cooldown_line[5] == 0
+        assert f_obs4.time_before_cooldown_line[5] == 0, f"{f_obs4.time_before_cooldown_line[5]} vs 0"
         assert info["is_illegal"]  # because cooldown is 1 when i took the action
 
         # now I can reco