This project aims to provide clean implementations of imitation and reward learning algorithms. Currently, we have implementations of the algorithms below. 'Discrete' and 'Continous' stands for whether the algorithm supports discrete or continuous action/state spaces respectively.
| Algorithm (+ link to paper) | API Docs | Discrete | Continuous |
|---|---|---|---|
| Behavioral Cloning | algorithms.bc |
✅ | ✅ |
| DAgger | algorithms.dagger |
✅ | ✅ |
| Density-Based Reward Modeling | algorithms.density |
✅ | ✅ |
| Maximum Causal Entropy Inverse Reinforcement Learning | algorithms.mce_irl |
✅ | ❌ |
| Adversarial Inverse Reinforcement Learning | algoritms.airl |
✅ | ✅ |
| Generative Adversarial Imitation Learning | algorithms.gail |
✅ | ✅ |
| Deep RL from Human Preferences | algorithms.preference_comparisons |
✅ | ✅ |
You can find the documentation here.
Installing the PyPI release is the standard way to use imitation, and the recommended way for most users.
pip install imitation
If you like, you can install imitation from source to contribute to the project or access the very last features before a stable release. You can do this by cloning the GitHub repository and running the installer directly. First run:
git clone http://github.com/HumanCompatibleAI/imitation && cd imitation.
For development mode, then run:
pip install -e ".[dev]"
This will run setup.py in development mode, and install the additional dependencies required for development. For regular use, run instead
pip install .
Additional extras are available depending on your needs. Namely, tests for running the test suite, docs for building the documentation, and parallel for parallelizing the training. The dev extra already installs the tests and docs dependencies automatically.
For macOS users, some packages are required to run experiments (see ./experiments/README.md for details). First, install Homebrew if not available (see Homebrew). Then, run:
brew install coreutils gnu-getopt parallel
Follow instructions to install mujoco_py v1.5 here.
We provide several CLI scripts as a front-end to the algorithms implemented in imitation. These use Sacred for configuration and replicability.
# Train PPO agent on pendulum and collect expert demonstrations. Tensorboard logs saved in quickstart/rl/
python -m imitation.scripts.train_rl with pendulum common.fast train.fast rl.fast fast common.log_dir=quickstart/rl/
# Train GAIL from demonstrations. Tensorboard logs saved in output/ (default log directory).
python -m imitation.scripts.train_adversarial gail with pendulum common.fast demonstrations.fast train.fast rl.fast fast demonstrations.rollout_path=quickstart/rl/rollouts/final.pkl
# Train AIRL from demonstrations. Tensorboard logs saved in output/ (default log directory).
python -m imitation.scripts.train_adversarial airl with pendulum common.fast demonstrations.fast train.fast rl.fast fast demonstrations.rollout_path=quickstart/rl/rollouts/final.pklTips:
- Remove the "fast" options from the commands above to allow training run to completion.
python -m imitation.scripts.train_rl print_configwill list Sacred script options. These configuration options are documented in each script's docstrings.
For more information on how to configure Sacred CLI options, see the Sacred docs.
See examples/quickstart.py for an example script that loads CartPole-v1 demonstrations and trains BC, GAIL, and AIRL models on that data.
We also implement a density-based reward baseline. You can find an example notebook here.
@misc{wang2020imitation,
author = {Wang, Steven and Toyer, Sam and Gleave, Adam and Emmons, Scott},
title = {The {\tt imitation} Library for Imitation Learning and Inverse Reinforcement Learning},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/HumanCompatibleAI/imitation}},
}
See Contributing to imitation for more information.