diff --git a/flatland/envs/rail_env.py b/flatland/envs/rail_env.py
index 1fa69f8a6a9c2fa5340bde5c3b20ad7b6fb80a83..3412ff6e416d2dee7f5475eff5a844b8acaf0184 100644
--- a/flatland/envs/rail_env.py
+++ b/flatland/envs/rail_env.py
@@ -742,7 +742,8 @@ class RailEnv(Environment):
         # full step penalty in this case
         if agent.malfunction_data['malfunction'] > 0:
             self.motionCheck.addAgent(i_agent, agent.position, agent.position)
-            self.rewards_dict[i_agent] += self.step_penalty * agent.speed_data['speed']
+            # agent will get penalty in step_agent2_cf
+            #self.rewards_dict[i_agent] += self.step_penalty * agent.speed_data['speed']
             return
 
         # Is the agent at the beginning of the cell? Then, it can take an action.