awesome-safe-reinforcement-learning

This repository is mainly about safe reinforcement learning and reinforcement learning under constraint. This is an ongoing project now, so keep an eye on it.

Related works are listed as follows:

Note that some works are just pre-printed articles.

Comprehensive version README (with Authors & Figures)

Survey

1. A Comprehensive Survey on Safe Reinforcement Learning JMLR 2015

Workshop

Benchmark

1. Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning arXiv 2021 | Github
2. Benchmarking Safe Exploration in Deep Reinforcement Learning preprint 2019 | Code
3. Multi-Agent Constrained Policy Optimisation arXiv 2022 | Code

Methodology

1. A Lyapunov-based Approach to Safe Reinforcement Learning NeurIPS 2018 | Note

2. Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks RA-L 2020 | Web

3. Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning CDC 2018 | Code

4. Learning-Based Model Predictive Control: Toward Safe Learning in Control Robotics, and Autonomous Systems 2020

5. COPTIDICE: OFFLINE CONSTRAINED REINFORCEMENT LEARNING VIA STATIONARY DISTRIBUTION CORRECTION ESTIMATION arXiv 2022