Merge branch 'develop' of github.com:Unity-Technologies/ml-agents into develop-nomaxstep-test

ml-agents-envs/mlagents/envs/brain.py

             reward=[x.reward if not np.isnan(x.reward) else 0 for x in agent_info_list],
             agents=agents,
             local_done=[x.done for x in agent_info_list],
-            max_reached=[x.max_step_reached for x in agent_info_list],
+            max_reached=[False for x in agent_info_list],
             action_mask=mask_actions,
         )
         return brain_info