elliemci/deadly_corridor_experiment

An APPO model trained on the doom_deadly_corridor environment.

This model was trained using Sample-Factory 2.1.1

Downloading the model

After installing Sample-Factory, download the model with:

python -m sample_factory.huggingface.load_from_hub -r elliemci/deadly_corridor_experiment

Using the model

To run the model after download, use the enjoy script corresponding to this environment:

python -m <path.to.enjoy.module> --algo=APPO --env=doom_deadly_corridor --train_dir=./train_dir --experiment=deadly_corridor_experiment

Training with this model

To continue training with this model, use the train script corresponding to this environment:

python -m <path.to.train.module> --algo=APPO --env=doom_deadly_corridor --train_dir=./train_dir --experiment=deadly_corridor_experiment --restart_behavior=resume --train_for_env_steps=10000000000