Fix example in README.md (#1830)

* Fix example in README.md

* Update changelog

---------

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>

README.md

@@ -127,7 +127,7 @@ import gymnasium as gym
 
 from stable_baselines3 import PPO
 
-env = gym.make("CartPole-v1")
+env = gym.make("CartPole-v1", render_mode="human")
 
 model = PPO("MlpPolicy", env, verbose=1)
 model.learn(total_timesteps=10_000)

docs/misc/changelog.rst

@@ -61,6 +61,7 @@ Documentation:
 - Updated callback code example
 - Updated export to ONNX documentation, it is now much simpler to export SB3 models with newer ONNX Opset!
 - Added video link to "Practical Tips for Reliable Reinforcement Learning" video
+- Added ``render_mode="human"`` in the README example (@marekm4)
 
 Release 2.2.1 (2023-11-17)
 --------------------------
@@ -1561,3 +1562,4 @@ And all the contributors:
 @anand-bala @hughperkins @sidney-tio @AlexPasqua @dominicgkerr @Akhilez @Rocamonde @tobirohrer @ZikangXiong @ReHoss
 @DavyMorgan @luizapozzobon @Bonifatius94 @theSquaredError @harveybellini @DavyMorgan @FieteO @jonasreiher @npit @WeberSamuel @troiganto
 @lutogniew @lbergmann1 @lukashass @BertrandDecoster @pseudo-rnd-thoughts @stefanbschneider @kyle-he @PatrickHelm @corentinlger
+@marekm4

setup.py

@@ -43,7 +43,7 @@ import gymnasium
 
 from stable_baselines3 import PPO
 
-env = gymnasium.make("CartPole-v1")
+env = gymnasium.make("CartPole-v1", render_mode="human")
 
 model = PPO("MlpPolicy", env, verbose=1)
 model.learn(total_timesteps=10_000)