Cannot run enjoy_vizdoom from model loaded from HF due to RuntimeError: Error(s) in loading state_dict for ActorCriticSharedWeights:

[ThanisornBest]

First I load the model from HF with
python -m sample_factory.huggingface.load_from_hub -r andrewzhang505/sample-factory-2-doom-battle -d ./train_dir
Then I ran
python -m sf_examples.vizdoom.enjoy_vizdoom --env=doom_battle --algo=APPO --experiment=sample-factory-2-doom-battle --train_dir=./train_dir

The error I got

Traceback (most recent call last):
  File "/home/thanisorn/miniconda3/envs/doom/lib/python3.9/runpy.py", line 197, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/thanisorn/miniconda3/envs/doom/lib/python3.9/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/home/thanisorn/Integral_Repo/sample-factory/sf_examples/vizdoom/enjoy_vizdoom.py", line 25, in <module>
    sys.exit(main())
  File "/home/thanisorn/Integral_Repo/sample-factory/sf_examples/vizdoom/enjoy_vizdoom.py", line 20, in main
    status = enjoy(cfg)
  File "/home/thanisorn/Integral_Repo/sample-factory/sample_factory/enjoy.py", line 137, in enjoy
    load_state_dict(cfg, actor_critic, device)
  File "/home/thanisorn/Integral_Repo/sample-factory/sample_factory/enjoy.py", line 98, in load_state_dict
    actor_critic.load_state_dict(checkpoint_dict["model"])
  File "/home/thanisorn/miniconda3/envs/doom/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2584, in load_state_dict
    raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for ActorCriticSharedWeights:
        Missing key(s) in state_dict: "encoder.basic_encoder.enc.mlp_layers.0.weight", "encoder.basic_encoder.enc.mlp_layers.0.bias". 
        Unexpected key(s) in state_dict: "encoder.basic_encoder.enc.fc_layers.0.weight", "encoder.basic_encoder.enc.fc_layers.0.bias".