franktiantt / emei

Emei is a toolkit for developing causal reinforcement learning algorithms.

Emei

Emei is an open source Python library for developing of causal model-based reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. Emei is a re-encapsulation of Openai Gym(will be replaced by Gymnasium soon).

To better support the model-based and the causal characteristics, Emei has the following features:

• providing a causal diagram corresponding to the environment
• friendly model-based RL interface
  • the reward and terminal functions that can be obtained directly
  • freeze and unfreeze is supported
• coming with offline dataset
• adjustment of frequency ratio is supported
  • for Mujoco, forward-euler method is added

install

install by cloning from github

# clone the repository
git clone https://github.com/FrankTianTT/emei.git
cd emei
# create conda env
conda create -n emei python=3.8
conda activate emei
# install emei and its dependent packages
pip install -e .

If there is no cuda in your device, it's convenient to install cuda and pytorch from conda directly (refer to pytorch):

# for example, in the case of cuda=11.3
conda install pytorch cudatoolkit=11.3 -c pytorch

install using pip

coming soon.