Setting up Training Environment...
Creating Liquid PPO Agent...
Using cpu device
Wrapping the env with a `Monitor` wrapper
Wrapping the env in a DummyVecEnv.
Starting Training (This may take a while)...
----------------------------------
| rollout/           |           |
|    ep_len_mean     | 1e+03     |
|    ep_rew_mean     | -2.12e+04 |
| time/              |           |
|    fps             | 464       |
|    iterations      | 1         |
|    time_elapsed    | 4         |
|    total_timesteps | 2048      |
----------------------------------
Traceback (most recent call last):
  File "/home/ylop/Documents/drone go brr/Drone-go-brrrrr/Drone-go-brrrrr/train.py", line 35, in <module>
    train()
    ~~~~~^^
  File "/home/ylop/Documents/drone go brr/Drone-go-brrrrr/Drone-go-brrrrr/train.py", line 28, in train
    model.learn(total_timesteps=total_timesteps, callback=checkpoint_callback)
    ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/ppo/ppo.py", line 311, in learn
    return super().learn(
           ~~~~~~~~~~~~~^
        total_timesteps=total_timesteps,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    ...<4 lines>...
        progress_bar=progress_bar,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 337, in learn
    self.train()
    ~~~~~~~~~~^^
  File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/ppo/ppo.py", line 275, in train
    loss.backward()
    ~~~~~~~~~~~~~^^
  File "/home/ylop/.local/lib/python3.14/site-packages/torch/_tensor.py", line 625, in backward
    torch.autograd.backward(
    ~~~~~~~~~~~~~~~~~~~~~~~^
        self, gradient, retain_graph, create_graph, inputs=inputs
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/ylop/.local/lib/python3.14/site-packages/torch/autograd/__init__.py", line 354, in backward
    _engine_run_backward(
    ~~~~~~~~~~~~~~~~~~~~^
        tensors,
        ^^^^^^^^
    ...<5 lines>...
        accumulate_grad=True,
        ^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/ylop/.local/lib/python3.14/site-packages/torch/autograd/graph.py", line 841, in _engine_run_backward
    return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
        t_outputs, *args, **kwargs
        ^^^^^^^^^^^^^^^^^^^^^^^^^^
    )  # Calls into the C++ engine to run the backward pass
    ^
RuntimeError: Trying to backward through the graph a second time (or directly access saved tensors after they have already been freed). Saved intermediate values of the graph are freed when you call .backward() or autograd.grad(). Specify retain_graph=True if you need to backward through the graph a second time or if you need to access saved tensors after calling backward.