diff --git a/rlzoo/distributed/start_dis_role.py b/rlzoo/distributed/start_dis_role.py
index 22c03bb..e24cee2 100755
--- a/rlzoo/distributed/start_dis_role.py
+++ b/rlzoo/distributed/start_dis_role.py
@@ -183,7 +183,7 @@ def run_server(agent, args, training_conf, env_conf, agent_conf):
 
     # save the final model
     rl_agent.save_ckpt(env_name)
-    print('server finished')
+    print('Server Finished.')
 
 
 def main(training_conf, env_conf, agent_conf):
@@ -201,6 +201,6 @@ def main(training_conf, env_conf, agent_conf):
     elif agent.role() == Role.Server:
         run_server(agent, args, training_conf, env_conf, agent_conf)
     else:
-        raise RuntimeError('invalid role')
+        raise RuntimeError('Invalid Role.')
 
     agent.barrier()
diff --git a/rlzoo/distributed/training_components.py b/rlzoo/distributed/training_components.py
index 3b5c447..a975245 100755
--- a/rlzoo/distributed/training_components.py
+++ b/rlzoo/distributed/training_components.py
@@ -4,15 +4,15 @@
 from rlzoo.algorithms.dppo_clip_distributed.dppo_clip import DPPO_CLIP
 from functools import partial
 
-# constants
+# Specify the training configurations
 training_conf = {
-    'total_step': int(1e7),
-    'traj_len': 200,
-    'train_n_traj': 2,
-    'save_interval': 10,
+    'total_step': int(1e7),  # overall training timesteps
+    'traj_len': 200,         # length of the rollout trajectory
+    'train_n_traj': 2,       # update the models after every certain number of trajectories for each learner 
+    'save_interval': 10,     # saving the models after every certain number of updates
 }
 
-# launch env settings
+# Specify the environment and launch it
 env_name, env_type = 'CartPole-v0', 'classic_control'
 env_maker = partial(build_env, env_name, env_type)
 temp_env = env_maker()
@@ -41,6 +41,7 @@ def build_network(observation_space, action_space, name='DPPO_CLIP'):
 
 
 def build_opt(actor_lr=1e-4, critic_lr=2e-4):
+    """ choose the optimizer for learning """
     import tensorflow as tf
     return [tf.optimizers.Adam(critic_lr), tf.optimizers.Adam(actor_lr)]
 
@@ -57,6 +58,6 @@ def build_opt(actor_lr=1e-4, critic_lr=2e-4):
 
 from rlzoo.distributed.start_dis_role import main
 
-print('start training')
+print('Start Training.')
 main(training_conf, env_conf, agent_conf)
-print('finished')
+print('Training Finished.')