Imitation Learning¶
The imitation library implements imitation learning algorithms on top of Stable-Baselines3, including:
Behavioral Cloning
DAgger with synthetic examples
It also provides CLI scripts for training and saving demonstrations from RL experts, and for training imitation learners on these demonstrations.
Installation¶
Installation requires Python 3.7+:
pip install imitation
CLI Quickstart¶
# Train PPO agent on cartpole and collect expert demonstrations
python -m imitation.scripts.expert_demos with fast cartpole log_dir=quickstart
# Train GAIL from demonstrations
python -m imitation.scripts.train_adversarial with fast gail cartpole rollout_path=quickstart/rollouts/final.pkl
# Train AIRL from demonstrations
python -m imitation.scripts.train_adversarial with fast airl cartpole rollout_path=quickstart/rollouts/final.pkl
Note
You can remove the fast
option to run training to completion. For more CLI options
and information on reading Tensorboard plots, see the
README.
Python Interface Quickstart¶
This example script uses the Python API to train BC, GAIL, and AIRL models on CartPole data.