https://github.com/vermouth1992/safe_rl_papers

A list of safe reinforcement learning papers
https://github.com/vermouth1992/safe_rl_papers

Last synced: about 2 months ago
JSON representation

A list of safe reinforcement learning papers

• Host: GitHub
• URL: https://github.com/vermouth1992/safe_rl_papers
• Owner: vermouth1992
• License: mit
• Created: 2019-12-07T09:13:08.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-01-09T22:33:11.000Z (about 5 years ago)
• Last Synced: 2023-03-27T16:13:06.343Z (almost 2 years ago)
• Size: 13.7 KB
• Stars: 18
• Watchers: 4
• Forks: 7
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# A List of Safe Reinforcement Learning Papers

## Algorithms

### Safe Exploration

- [Safe Exploration in Continuous Action Spaces](https://arxiv.org/pdf/1801.08757.pdf)

- [Safe Exploration for Interactive Machine Learning](https://arxiv.org/abs/1910.13726)

- [Safely Probabilistically Complete Real-Time Planning and Exploration in Unknown Environments](https://arxiv.org/pdf/1811.07834.pdf)

### Safe Planning

- [Safe Planning via Model Predictive Shielding](https://arxiv.org/pdf/1905.10691.pdf)

### Policy Learning

- [A Lyapunov-based Approach to Safe Reinforcement Learning](https://arxiv.org/pdf/1805.07708.pdf)

- [Constrained Policy Optimization](https://arxiv.org/abs/1705.10528)

- [End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks](https://rcheng805.github.io/files/aaai2019.pdf)

  - [Code](https://github.com/rcheng805/RL-CBF)

- [Risk-Constrained Reinforcement Learning with Percentile Risk Criteria](https://arxiv.org/pdf/1512.01629.pdf)

- [Convergent Policy Optimization for Safe Reinforcement Learning](https://arxiv.org/abs/1910.12156)

- [Lyapunov-based Safe Policy Optimization for Continuous Control](https://arxiv.org/pdf/1901.10031.pdf)

- [Neural Lyapunov Control](http://papers.nips.cc/paper/8587-neural-lyapunov-control.pdf)

- [CAQL: CONTINUOUS ACTION Q-LEARNING](https://arxiv.org/pdf/1909.12397.pdf)

### Safe Reinforcement Learning with Stability Guarantees

- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://papers.nips.cc/paper/6692-safe-model-based-reinforcement-learning-with-stability-guarantees.pdf)

- [The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems](https://arxiv.org/pdf/1808.00924.pdf)

- [Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processes](https://arxiv.org/pdf/1603.04915.pdf)

- [Code](https://github.com/befelix/safe_learning)

### Human in the loop

- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://arxiv.org/abs/1707.05173)

## Surveys

[A Comprehensive Survey on Safe Reinforcement Learning](http://www.jmlr.org/papers/volume16/garcia15a/garcia15a.pdf)

## Benchmarks

- [Benchmarking Safe Exploration in Deep Reinforcement Learning](https://d4mucfpksywv.cloudfront.net/safexp-short.pdf)

- [The city learn challenge](https://sites.google.com/view/citylearnchallenge)

  - [Code](https://github.com/intelligent-environments-lab/CityLearn)

## Thesis

[SAFE REINFORCEMENT LEARNING](https://people.cs.umass.edu/~pthomas/papers/Thomas2015c.pdf)

## Lectures

[Safe Reinforcement Learning](https://web.stanford.edu/class/cs234/slides/2017/cs234_guest_lecture_safe_rl.pdf)