bugfix in observation and prediction for tree observation

examples/training_example.py

@@ -80,7 +80,6 @@ for trials in range(1, n_trials + 1):
         # Environment step which returns the observations for all agents, their corresponding
         # reward and whether their are done
         next_obs, all_rewards, done, _ = env.step(action_dict)
-
         # Update replay buffer and train agent
         for a in range(env.get_num_agents()):
             agent.step((obs[a], action_dict[a], all_rewards[a], next_obs[a], done[a]))