diff --git a/flatland/__init__.py b/flatland/__init__.py
index a51361920643b32d156c257baf6d3469b916d0b9..2bb8fee4b5eacf7ebcf7fae9e5c94ed6da5695ff 100644
--- a/flatland/__init__.py
+++ b/flatland/__init__.py
@@ -4,4 +4,4 @@
 
 __author__ = """S.P. Mohanty"""
 __email__ = 'mohanty@aicrowd.com'
-__version__ = '0.3.6'
+__version__ = '0.3.10'
diff --git a/flatland/evaluators/service.py b/flatland/evaluators/service.py
index 21a5e63f3a0e58ff915c3743eac56250435b5ee4..3ad0a97598c8beb66fc164eb45b670c87f3c96f9 100644
--- a/flatland/evaluators/service.py
+++ b/flatland/evaluators/service.py
@@ -17,6 +17,7 @@ import time
 import traceback
 import crowdai_api
 import timeout_decorator
+import random
 
 
 use_signals_in_timeout = True
@@ -74,6 +75,10 @@ class FlatlandRemoteEvaluationService:
         self.test_env_folder = test_env_folder
         self.video_generation_envs = video_generation_envs
         self.env_file_paths = self.get_env_filepaths()
+        random.shuffle(self.env_file_paths)
+        print(self.env_file_paths)
+        # Shuffle all the env_file_paths for more exciting videos
+        # and for more uniform time progression
 
         # Logging and Reporting related vars
         self.verbose = verbose
@@ -352,9 +357,9 @@ class FlatlandRemoteEvaluationService:
         progress = np.clip(
                     self.simulation_count * 1.0 / len(self.env_file_paths),
                     0, 1)
-        mean_reward = np.mean(self.simulation_rewards)
-        mean_normalized_reward = np.mean(self.simulation_rewards_normalized)
-        mean_percentage_complete = np.mean(self.simulation_percentage_complete)
+        mean_reward = round(np.mean(self.simulation_rewards), 2)
+        mean_normalized_reward = round(np.mean(self.simulation_rewards_normalized), 2)
+        mean_percentage_complete = round(np.mean(self.simulation_percentage_complete), 3)
         self.evaluation_state["state"] = "IN_PROGRESS"
         self.evaluation_state["progress"] = progress
         self.evaluation_state["simulation_count"] = self.simulation_count
@@ -457,9 +462,9 @@ class FlatlandRemoteEvaluationService:
                 """
             )
         
-        mean_reward = np.mean(self.simulation_rewards)
-        mean_normalized_reward = np.mean(self.simulation_rewards_normalized)
-        mean_percentage_complete = np.mean(self.simulation_percentage_complete)
+        mean_reward = round(np.mean(self.simulation_rewards), 2)
+        mean_normalized_reward = round(np.mean(self.simulation_rewards_normalized), 2)
+        mean_percentage_complete = round(np.mean(self.simulation_percentage_complete), 3)
 
         if self.visualize and len(os.listdir(self.vizualization_folder_name)) > 0:
             # Generate the video
diff --git a/requirements_dev.txt b/requirements_dev.txt
index 2c3fce762e2cc9f66890ad6def2f7e8c005305c9..e02da21600b9cf0574457e915c69474afe0eff35 100644
--- a/requirements_dev.txt
+++ b/requirements_dev.txt
@@ -1,6 +1,5 @@
 # contains all requirements to run the tests by running ```tox -e py36,py37```
 tox>=3.5.2
-twine>=1.12.1
 pytest>=3.8.2
 pytest-runner>=4.2
 Click>=7.0
@@ -14,7 +13,6 @@ CairoSVG>=2.3.1
 msgpack>=0.6.1
 msgpack-numpy>=0.4.4.0
 svgutils>=0.3.1
-screeninfo>=0.3.1
 pyarrow>=0.13.0
 importlib-metadata>=0.17
 importlib-resources>=1.0.1
diff --git a/setup.cfg b/setup.cfg
index 457dcd2bea6007d073912a7199da885f90e34d7c..580e6accda68402e5f8ca70577cd68eb5b5ad173 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.6
+current_version = 0.3.10
 commit = True
 tag = True
 
diff --git a/setup.py b/setup.py
index 5299efb0744280a1c0b10d125db7af03e1d7e8e6..48ddd96d47c1e542008e2ad93c60b7bf2b43b410 100644
--- a/setup.py
+++ b/setup.py
@@ -79,6 +79,6 @@ setup(
     test_suite='tests',
     tests_require=test_requirements,
     url='https://gitlab.aicrowd.com/flatland/flatland',
-    version='0.3.6',
+    version='0.3.10',
     zip_safe=False,
 )