seals 0.1.0

Suite of Environments for Algorithms that Learn Specifications

Status: alpha, pre-release.

The CHAI Suite of Environments for Algorithms that Learn Specifications (SEALS) is a toolkit for evaluating specification learning algorithms, such as reward or imitation learning. The environments are compatible with Gym, but are designed to test algorithms that learn from user data, without requiring a procedurally specified reward function.

This is currently a work-in progress. While you are welcome to use the repository, we may make breaking changes at any time without prior notice. We intend for it to eventually contain:

• A suite of diagnostic tasks for reward learning.
• Wrappers around common RL benchmark environments that help to avoid common pitfalls in benchmarking (e.g. by masking visible score counters in Gym Atari tasks).
• New challenge tasks for specification learning algorithms.

You may also be interested in our sister project imitation, providing implementations of a variety of imitation and reward learning algorithms.

Quickstart

To install the latest release from PyPI, run:

pip install seals

All SEALS environments are available in the Gym registry. Simply import it and then use as you would with your usual RL or specification learning algroithm:

import gym
import seals

env = gym.make('seals/CartPole-v0')

We make releases periodically, but if you wish to use the latest versino of the code, you can install directly from Git master:

pip install git+https://github.com/HumanCompatibleAI/seals.git

Contributing

For development, clone the source code and create a virtual environment for this project:

git clone [e-mail]:HumanCompatibleAI/seals.git
cd seals
./ci/build_venv.sh
pip install -e .[dev]  # install extra tools useful for development

Code style

We follow a PEP8 code style with line length 88, and typically follow the Google Code Style Guide, but defer to PEP8 where they conflict. We use the black autoformatter to avoid arguing over formatting. Docstrings follow the Google docstring convention defined here, with an extensive example in the Sphinx docs.

All PRs must pass linting via the ci/code_checks.sh script. It is convenient to install this as a commit hook:

ln -s ../../ci/code_checks.sh .git/hooks/pre-commit

Tests

We use pytest for unit tests and codecov for code coverage. We also use pytype for type checking.

Workflow

Trivial changes (e.g. typo fixes) may be made directly by maintainers. Any non-trivial changes must be proposed in a PR and approved by at least one maintainer. PRs must pass the continuous integration tests (CircleCI linting, type checking, unit tests and CodeCov) to be merged.

It is often helpful to open an issue before proposing a PR, to allow for discussion of the design before coding commences.