ammarhydr/SAC-Lagrangian

PyTorch implementation of Constrained Reinforcement Learning for Soft Actor Critic Algorithm

Python

SAC-Lagrangian

This repository is for the implementation of Constrained Soft Actor Critic SAC with lagrange multiplier in PyTorch.

Pre-requisites

PyTorch (The code is tested on PyTorch 1.2.0.)
OpenAI Safety Gym
MuJoCo mujoco-py

Training

To train the model in the repository, run this command:

python SACLagrangian.py