diff --git a/docs/guide/imitation.rst b/docs/guide/imitation.rst index df7895c..c4a0726 100644 --- a/docs/guide/imitation.rst +++ b/docs/guide/imitation.rst @@ -10,46 +10,10 @@ imitation learning algorithms on top of Stable-Baselines3, including: - `DAgger `_ with synthetic examples - `Adversarial Inverse Reinforcement Learning `_ (AIRL) - `Generative Adversarial Imitation Learning `_ (GAIL) + - `Deep RL from Human Preferences `_ (DRLHP) - -It also provides `CLI scripts <#cli-quickstart>`_ 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. +You can install imitation with ``pip install imitation``. The `imitation +documentation `_ has more details +on how to use the library, including `a quick start guide +`_ +for the impatient.