diff --git a/envs/agents/deepvss/agents/agentDDPGMA.py b/envs/agents/deepvss/agents/agentDDPGMA.py
index 8ca4ae52..f3241751 100644
--- a/envs/agents/deepvss/agents/agentDDPGMA.py
+++ b/envs/agents/deepvss/agents/agentDDPGMA.py
@@ -154,7 +154,7 @@ def play(params, net, device, exp_queue, agent_env, test, writer, collected_samp
                     exp_queue.put(exp)
 
             if test:
-                agent_env.render()
+                agent_env.render('human')
 
             states = next_states
 
diff --git a/envs/rc_gym/vss/env_ma/vss_gym_ma.py b/envs/rc_gym/vss/env_ma/vss_gym_ma.py
index 574d36c1..9fc8cfb5 100644
--- a/envs/rc_gym/vss/env_ma/vss_gym_ma.py
+++ b/envs/rc_gym/vss/env_ma/vss_gym_ma.py
@@ -264,7 +264,7 @@ def _calculate_reward_and_done(self):
                         w_move * move_reward + \
                         w_energy * energy_penalty
 
-                    reward[f'robot_{idx}'] = rew
+                    reward[f'robot_{idx}'] += rew
                     self.reward_shaping_total[f'robot_{idx}']['move'] += w_move * move_reward  # noqa
                     self.reward_shaping_total[f'robot_{idx}']['energy'] += w_energy * energy_penalty  # noqa