Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

A-Crab: Actor-Critic Regularized by Average Bellman error

This repository contains the code to reproduce the experimental results of A-Crab algorithm in the paper Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning by Hanlin Zhu, Paria Rashidinejad, and Jiantao Jiao. Most of the code and instructions are adapted from and follow the logic in the lightATAC repo.

Setup

Step 1: Clone the repository.

git clone https://github.com/zhuhl98/ACrab.git

or

git clone git@github.com:zhuhl98/ACrab.git

Step 2: Create a conda environment.

conda create -n ACrab python=3.9
conda activate ACrab
cd ACrab

Step 3: To install, run

pip install -e .

Step 4: It uses mujoco210, which can be installed, if needed, following the commands below.

bash install.sh
echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin:/usr/lib/nvidia" >> ~/.bashrc
source ~/.bashrc
conda activate ACrab

Step 5: If necessary, downgrade Cython:

pip install Cython==0.29.36

Step 6: You can start the training by running, e.g.,

python main.py --log_dir ./tmp_results --env_name hopper-medium-expert-v2 --beta 1 --C_infty 1

More instructions can be found in main.py, and please see the original paper for hyperparameters (e.g., beta, C_infty). The code was tested with python 3.9.

About

No description, website, or topics provided.

Resources

Stars

2 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages