Fix issues due to newer version of protobuf and sphinx (#924)

docs/conf.py

@@ -100,7 +100,7 @@ master_doc = "index"
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = "en"
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.

docs/misc/changelog.rst

@@ -4,7 +4,7 @@ Changelog
 ==========
 
 
-Release 1.5.1a6 (WIP)
+Release 1.5.1a7 (WIP)
 ---------------------------
 
 Breaking Changes:
@@ -27,6 +27,7 @@ Bug Fixes:
 - Fixed a bug in ``DummyVecEnv``'s and ``SubprocVecEnv``'s seeding function. None value was unchecked (@ScheiklP)
 - Fixed a bug where ``EvalCallback`` would crash when trying to synchronize ``VecNormalize`` stats when observation normalization was disabled
 - Added a check for unbounded actions
+- Fixed issues due to newer version of protobuf (tensorboard) and sphinx
 
 Deprecations:
 ^^^^^^^^^^^^^

setup.py

@@ -43,10 +43,10 @@ import gym
 
 from stable_baselines3 import PPO
 
-env = gym.make('CartPole-v1')
+env = gym.make("CartPole-v1")
 
-model = PPO('MlpPolicy', env, verbose=1)
-model.learn(total_timesteps=10000)
+model = PPO("MlpPolicy", env, verbose=1)
+model.learn(total_timesteps=10_000)
 
 obs = env.reset()
 for i in range(1000):
@@ -57,12 +57,12 @@ for i in range(1000):
         obs = env.reset()
 ```
 
-Or just train a model with a one liner if [the environment is registered in Gym](https://github.com/openai/gym/wiki/Environments) and if [the policy is registered](https://stable-baselines3.readthedocs.io/en/master/guide/custom_policy.html):
+Or just train a model with a one liner if [the environment is registered in Gym](https://www.gymlibrary.ml/content/environment_creation/) and if [the policy is registered](https://stable-baselines3.readthedocs.io/en/master/guide/custom_policy.html):
 
 ```python
 from stable_baselines3 import PPO
 
-model = PPO('MlpPolicy', 'CartPole-v1').learn(10000)
+model = PPO("MlpPolicy", "CartPole-v1").learn(10_000)
 ```
 
 """  # noqa:E501
@@ -121,6 +121,9 @@ setup(
             "pillow",
             # Tensorboard support
             "tensorboard>=2.2.0",
+            # Protobuf >= 4 has breaking changes
+            # which does play well with tensorboard
+            "protobuf~=3.19.0",
             # Checking memory taken by replay buffer
             "psutil",
         ],

stable_baselines3/version.txt

@@ -1 +1 @@
-1.5.1a6
+1.5.1a7