A Lyapunov-based Approach to Safe Reinforcement Learning

20 May 2018

Yinlam Chow

Ofir Nachum

Edgar A. Duénez-Guzmán

Mohammad Ghavamzadeh

ArXiv PDF HTML

Papers citing "A Lyapunov-based Approach to Safe Reinforcement Learning"

50 / 286 papers shown

Title
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems Bhavya Sukhija M. Turchetta David Lindner Andreas Krause Sebastian Trimpe Dominik Baumann 36 17 0 24 Jan 2022
Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environments Hengbo Ma Bike Zhang Masayoshi Tomizuka Koushil Sreenath 20 23 0 04 Jan 2022
Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles Xinglong Zhang Yaoqian Peng Biao Luo Wei Pan Xin Xu Haibin Xie 27 11 0 18 Dec 2021
Cooperation for Scalable Supervision of Autonomy in Mixed Traffic Cameron Hickert Sirui Li Cathy Wu 28 5 0 14 Dec 2021
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance Michael Luo Ashwin Balakrishna Brijen Thananjeyan Suraj Nair Julian Ibarz Jie Tan Chelsea Finn Ion Stoica Ken Goldberg OffRL 38 4 0 07 Dec 2021
Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey M. Askarpour Alan Wassyng M. Lawford R. Paige Z. Diskin 27 0 0 29 Nov 2021
A note on stabilizing reinforcement learning Pavel Osinenko Grigory Yaremenko Ilya Osokin 14 2 0 24 Nov 2021
Explicit Explore, Exploit, or Escape ( $E^4$ ): near-optimal safety-constrained reinforcement learning in polynomial time David M. Bossens Nick Bishop 14 8 0 14 Nov 2021
DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning Zhaoxing Yang Rong Ding Haiming Jin Yifei Wei Haoyi You Guiyun Fan Xiaoying Gan Xinbing Wang 40 4 0 10 Nov 2021
Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning Stefan Radic Webster Peter A. Flach 29 3 0 09 Nov 2021
Infinite Time Horizon Safety of Bayesian Neural Networks Mathias Lechner Dorde Zikelic K. Chatterjee T. Henzinger 13 18 0 04 Nov 2021
Learning to Be Cautious Montaser Mohammedalamen Dustin Morrill Alexander Sieusahai Yash Satsangi Michael Bowling 18 3 0 29 Oct 2021
DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention D. Mguni Usman Islam Taher Jafferjee Xiuling Zhang Joel Jennings Aivar Sootla Changmin Yu Ziyan Wang Jun Wang Yaodong Yang OffRL 31 7 0 27 Oct 2021
Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes Sihan Zeng Thinh T. Doan Justin Romberg 102 17 0 21 Oct 2021
Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process Tianjiao Li Ziwei Guan Shaofeng Zou Tengyu Xu Yingbin Liang Guanghui Lan 29 26 0 20 Oct 2021
Safe Autonomous Racing via Approximate Reachability on Ego-vision Bingqing Chen Jonathan M Francis Jean Oh Eric Nyberg Sylvia Herbert 59 14 0 14 Oct 2021
Safe Driving via Expert Guided Policy Optimization Zhenghao Peng Quanyi Li Chunxiao Liu Bolei Zhou OffRL 31 41 0 13 Oct 2021
Safe Reinforcement Learning Using Robust Control Barrier Functions Y. Emam Gennaro Notomista Paul Glotfelter Z. Kira M. Egerstedt OffRL 24 39 0 11 Oct 2021
Multi-Agent Constrained Policy Optimisation Shangding Gu J. Kuba Munning Wen Ruiqing Chen Ziyan Wang Zheng Tian Jun Wang Alois Knoll Yaodong Yang 98 49 0 06 Oct 2021
SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction Haimin Hu Kensuke Nakamura J. F. Fisac 39 23 0 02 Oct 2021
Explanation-Aware Experience Replay in Rule-Dense Environments Francesco Sovrano Alex Raymond Amanda Prorok 11 7 0 29 Sep 2021
RMPs for Safe Impedance Control in Contact-Rich Manipulation S. Shaw Ben Abbatematteo George Konidaris 26 13 0 24 Sep 2021
Data Generation Method for Learning a Low-dimensional Safe Region in Safe Reinforcement Learning Zhehua Zhou Ozgur S. Oguz Yi Ren M. Leibold M. Buss OffRL 22 0 0 10 Sep 2021
Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems Fangda Gu He Yin L. Ghaoui Murat Arcak Peter M. Seiler Ming Jin 25 25 0 08 Sep 2021
Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning Lukas Brunke Melissa Greeff Adam W. Hall Zhaocong Yuan Siqi Zhou Jacopo Panerati Angela P. Schoellig OffRL 34 603 0 13 Aug 2021
Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty R. Russel M. Benosman J. Baar Radu Corcodel 17 5 0 05 Aug 2021
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations Yuping Luo Tengyu Ma OffRL 36 43 0 04 Aug 2021
Lyapunov-based uncertainty-aware safe reinforcement learning Ashkan B. Jeddi Nariman L. Dehghani A. Shafieezadeh 19 7 0 29 Jul 2021
Autonomous Reinforcement Learning via Subgoal Curricula Archit Sharma Abhishek Gupta Sergey Levine Karol Hausman Chelsea Finn 27 27 0 27 Jul 2021
Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics Ya-Chien Chang Sicun Gao 20 57 0 11 Jul 2021
Safe Exploration by Solving Early Terminated MDP Hao Sun Ziping Xu Meng Fang Zhenghao Peng Jiadong Guo Bo Dai Bolei Zhou 19 16 0 09 Jul 2021
Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research J. Luis E. Crawley B. Cameron OffRL 27 6 0 07 Jul 2021
Density Constrained Reinforcement Learning Zengyi Qin Yuxiao Chen Chuchu Fan 17 35 0 24 Jun 2021
Safe Reinforcement Learning Using Advantage-Based Intervention Nolan Wagener Byron Boots Ching-An Cheng 34 52 0 16 Jun 2021
Safe Reinforcement Learning with Linear Function Approximation Sanae Amani Christos Thrampoulidis Lin F. Yang 6 35 0 11 Jun 2021
A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes Honghao Wei Xin Liu Lei Ying 29 21 0 03 Jun 2021
Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs Harsh Satija Philip S. Thomas Joelle Pineau Romain Laroche OffRL 40 21 0 31 May 2021
Safe Pontryagin Differentiable Programming Wanxin Jin Shaoshuai Mou George J. Pappas 30 39 0 31 May 2021
GoSafe: Globally Optimal Safe Robot Learning Dominik Baumann A. Marco M. Turchetta Sebastian Trimpe 11 37 0 27 May 2021
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence Wenhao Zhan Shicong Cen Baihe Huang Yuxin Chen Jason D. Lee Yuejie Chi 26 76 0 24 May 2021
Learning to Act Safely with Limited Exposure and Almost Sure Certainty Agustin Castellano Hancheng Min J. Bazerque Enrique Mallada 29 4 0 18 May 2021
Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction Helge Spieker 28 3 0 24 Apr 2021
Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning Songan Zhang Lu Wen H. Peng H. E. Tseng 27 10 0 18 Apr 2021
Safe Continuous Control with Constrained Model-Based Policy Optimization Moritz A. Zanger Karam Daaboul J. Marius Zöllner 19 19 0 14 Apr 2021
Almost Surely Stable Deep Dynamics Nathan P. Lawrence Philip D. Loewen M. Forbes Johan U. Backstrom R. Bhushan Gopaluni BDL 42 20 0 26 Mar 2021
Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method Duo Xu Faramarz Fekri 13 7 0 22 Mar 2021
Lyapunov Barrier Policy Optimization Harshit S. Sikchi Wenxuan Zhou David Held 34 14 0 16 Mar 2021
Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization Jyun-Li Lin Wei-Ting Hung Shangtong Yang Ping-Chun Hsieh Xi Liu 35 14 0 22 Feb 2021
Provably Correct Training of Neural Network Controllers Using Reachability Analysis Xiaowu Sun Yasser Shoukry 22 7 0 22 Feb 2021
Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges Xin Chen Guannan Qu Yujie Tang S. Low Na Li 24 227 0 27 Jan 2021