Update docs, Provide the env when loading the model (#327) (#330)

* Provide the env when loading the model (#327)

* Update docs/misc/changelog.rst

Co-authored-by: Anssi <kaneran21@hotmail.com>

docs/guide/custom_policy.rst

@@ -42,7 +42,7 @@ using ``policy_kwargs`` parameter:
 
   del model
   # the policy_kwargs are automatically loaded
-  model = PPO.load("ppo_cartpole")
+  model = PPO.load("ppo_cartpole", env=env)
 
 
 Custom Feature Extractor

docs/guide/examples.rst

@@ -76,7 +76,7 @@ In the following example, we will train, save and load a DQN model on the Lunar
   del model  # delete trained model to demonstrate loading
 
   # Load the trained agent
-  model = DQN.load("dqn_lunar")
+  model = DQN.load("dqn_lunar", env=env)
 
   # Evaluate the agent
   # NOTE: If you use wrappers with your environment that modify rewards,
@@ -335,9 +335,6 @@ will compute a running average and standard deviation of input features (it can
   # To demonstrate loading
   del model, env
 
-  # Load the agent
-  model = PPO.load(log_dir + "ppo_halfcheetah")
-
   # Load the saved statistics
   env = DummyVecEnv([lambda: gym.make("HalfCheetahBulletEnv-v0")])
   env = VecNormalize.load(stats_path, env)
@@ -346,6 +343,9 @@ will compute a running average and standard deviation of input features (it can
   # reward normalization is not needed at test time
   env.norm_reward = False
 
+  # Load the agent
+  model = PPO.load(log_dir + "ppo_halfcheetah", env=env)
+
 
 Hindsight Experience Replay (HER)
 ---------------------------------

docs/misc/changelog.rst

@@ -73,6 +73,7 @@ Documentation:
 - Updated custom policy doc (separate policy architecture recommended)
 - Added a note about OpenCV headless version
 - Corrected typo on documentation (@mschweizer)
+- Provide the environment when loading the model in the examples (@lorepieri8)
 
 
 Pre-Release 0.10.0 (2020-10-28)
@@ -548,4 +549,4 @@ And all the contributors:
 @flodorner @KuKuXia @NeoExtended @PartiallyTyped @mmcenta @richardwu @kinalmehta @rolandgvc @tkelestemur @mloo3
 @tirafesi @blurLake @koulakis @joeljosephjin @shwang @rk37 @andyshih12 @RaphaelWag @xicocaio
 @diditforlulz273 @liorcohen5 @ManifoldFR @mloo3 @SwamyDev @wmmc88 @megan-klaiber @thisray
-@tfederico @hn2 @LucasAlegre @AptX395 @zampanteymedio @decodyng @ardabbour @lorenz-h @mschweizer
+@tfederico @hn2 @LucasAlegre @AptX395 @zampanteymedio @decodyng @ardabbour @lorenz-h @mschweizer @lorepieri8