You must pass an environment when using `HerReplayBuffer`

[izvvv]

❓ Question

Cell In[11], line 8 5 env.unwrapped.config["obstacles_count"] = 0
6 env.reset() ----> 8 model = TD3.load("models/vvparking-v2.0/TD3") 10 replay_buffer = HerReplayBuffer(env=env, buffer_size=1000000,n_sampled_goal=4, goal_selection_strategy='future') 12 for episode in trange(N_EPISODES, desc="Test episodes"):

File e:\Anaconda\envs\Graduation\Lib\site-packages\stable_baselines3\common\base_class.py:737, in BaseAlgorithm.load(cls, path, env, device, custom_objects, print_system_info, force_reset, **kwargs) 735 model.dict.update(data) 736 model.dict.update(kwargs) --> 737 model._setup_model() 739 try: 740 # put state_dicts back in place 741 model.set_parameters(params, exact_match=True, device=device)

File e:\Anaconda\envs\Graduation\Lib\site-packages\stable_baselines3\td3\td3.py:140, in TD3._setup_model(self) 139 def _setup_model(self) -> None: --> 140 super()._setup_model() 141 self._create_aliases() 142 # Running mean and running var

File e:\Anaconda\envs\Graduation\Lib\site-packages\stable_baselines3\common\off_policy_algorithm.py:187, in OffPolicyAlgorithm._setup_model(self) 185 replay_buffer_kwargs = self.replay_buffer_kwargs.copy() 186 if issubclass(self.replay_buffer_class, HerReplayBuffer): --> 187 assert self.env is not None, "You must pass an environment when using HerReplayBuffer" 188 replay_buffer_kwargs["env"] = self.env 189 self.replay_buffer = self.replay_buffer_class( 190 self.buffer_size, 191 self.observation_space, (...) 196 **replay_buffer_kwargs, 197 )

AssertionError: You must pass an environment when using HerReplayBuffer

Pls how to fix it

Checklist

• [X] I have checked that there is no similar issue in the repo
• [X] I have read the documentation
• [X] If code there is, it is minimal and working
• [X] If code there is, it is formatted using the markdown code blocks for both code and stack traces.