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
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs Theodore H. Moskovitz Brendan O'Donoghue Vivek Veeriah Sebastian Flennerhag Satinder Singh Tom Zahavy 50 19 0 02 Feb 2023
Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach Haimin Hu David Isele S. Bae J. F. Fisac 35 17 0 01 Feb 2023
Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties Hao Jiang Tien Mai Pradeep Varakantham M. Hoang OffRL 20 2 0 27 Jan 2023
Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation Chenxi Yang Greg Anderson Swarat Chaudhuri 34 1 0 26 Jan 2023
AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning Tairan He Weiye Zhao Changliu Liu OffRL 39 17 0 24 Jan 2023
Quasi-optimal Reinforcement Learning with Continuous Actions Yuhan Li Wenzhuo Zhou Ruoqing Zhu OffRL 32 5 0 21 Jan 2023
A Policy Optimization Method Towards Optimal-time Stability Shengjie Wang Lan Fengb Xiang Zheng Yu-wen Cao Oluwatosin Oseni Haotian Xu Tao Zhang Yang Gao 39 1 0 02 Jan 2023
Don't do it: Safer Reinforcement Learning With Rule-based Guidance Ekaterina Nikonova Cheng Xue Jochen Renz 32 0 0 28 Dec 2022
Lexicographic Multi-Objective Reinforcement Learning Joar Skalse Lewis Hammond Charlie Griffin Alessandro Abate 30 20 0 28 Dec 2022
Online Shielding for Reinforcement Learning Bettina Könighofer Julian Rudolf Alexander Palmisano Martin Tappler Roderick Bloem OffRL 14 21 0 04 Dec 2022
Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability Whiyoung Jung Myungsik Cho Jongeui Park Young-Jin Sung 38 4 0 28 Nov 2022
Safety-Constrained Policy Transfer with Successor Features Zeyu Feng Bowen Zhang Jianxin Bi Harold Soh 32 4 0 10 Nov 2022
A Transfer Learning Approach for UAV Path Design with Connectivity Outage Constraint G. Fontanesi Anding Zhu M. Arvaneh Hamed Ahmadi 19 16 0 07 Nov 2022
Provable Safe Reinforcement Learning with Binary Feedback Andrew Bennett Dipendra Kumar Misra Nathan Kallus OffRL 36 4 0 26 Oct 2022
Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems Eric Yang Yu Zhizhen Qin Min Kyung Lee Sicun Gao OffRL 37 15 0 22 Oct 2022
Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization T. Lew Sumeet Singh M. Prats Jeffrey Bingham Jonathan Weisz ... Fei Xia Peng Xu Tingnan Zhang Jie Tan Montserrat Gonzalez 35 15 0 19 Oct 2022
Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm Ashish Kumar Jayant S. Bhatnagar OffRL 21 38 0 14 Oct 2022
Near-Optimal Multi-Agent Learning for Safe Coverage Control Manish Prajapat M. Turchetta Melanie Zeilinger Andreas Krause 35 14 0 12 Oct 2022
Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees Dorde Zikelic Mathias Lechner T. Henzinger K. Chatterjee 26 22 0 11 Oct 2022
Learning Provably Stabilizing Neural Controllers for Discrete-Time Stochastic Systems Matin Ansaripour K. Chatterjee T. Henzinger Mathias Lechner Dorde Zikelic 42 5 0 11 Oct 2022
Neurosymbolic Motion and Task Planning for Linear Temporal Logic Tasks Xiaowu Sun Yasser Shoukry 50 11 0 11 Oct 2022
Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning Zih-Yun Chiu Yi-Lin Tuan William Yang Wang Michael C. Yip OffRL 32 3 0 07 Oct 2022
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments Yixuan Wang S. Zhan Ruochen Jiao Zhilu Wang Wanxin Jin Zhuoran Yang Zhaoran Wang Chao Huang Qi Zhu 32 48 0 29 Sep 2022
Guiding Safe Exploration with Weakest Preconditions Greg Anderson Swarat Chaudhuri Işıl Dillig 52 6 0 28 Sep 2022
Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction Puze Liu Kuo Zhang Davide Tateo Snehal Jauhri Zhiyuan Hu Jan Peters Georgia Chalvatzaki 47 17 0 27 Sep 2022
Constrained Update Projection Approach to Safe Policy Optimization Long Yang Jiaming Ji Juntao Dai Linrui Zhang Binbin Zhou Pengfei Li Yaodong Yang Gang Pan 41 43 0 15 Sep 2022
Robust Constrained Reinforcement Learning Yue Wang Fei Miao Shaofeng Zou 39 12 0 14 Sep 2022
A framework for online, stabilizing reinforcement learning Grigory Yaremenko Georgiy Malaniya Pavel Osinenko OffRL OnRL 18 1 0 18 Jul 2022
Effects of Safety State Augmentation on Safe Exploration Aivar Sootla Alexander I. Cowen-Rivers Jun Wang H. Ammar OffRL 40 0 0 06 Jun 2022
Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs Dongsheng Ding Kaipeng Zhang Jiali Duan Tamer Bacsar Mihailo R. Jovanović 28 19 0 06 Jun 2022
KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems Sahin Lale Yuanyuan Shi Guannan Qu Kamyar Azizzadenesheli Adam Wierman Anima Anandkumar 25 9 0 03 Jun 2022
Reinforcement Learning with a Terminator Guy Tennenholtz Nadav Merlis Lior Shani Shie Mannor Uri Shalit Gal Chechik Assaf Hallak Gal Dalal 25 5 0 30 May 2022
A Review of Safe Reinforcement Learning: Methods, Theory and Applications Shangding Gu Longyu Yang Yali Du Guang Chen Florian Walter Jun Wang Alois C. Knoll OffRL AI4TS 117 241 0 20 May 2022
Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking Hanna Krasowski Jakob Thumm Marlon Müller Lukas Schäfer Xiao Wang Matthias Althoff 88 20 0 13 May 2022
Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models Zhongyu Li Jun Zeng A. Thirugnanam Koushil Sreenath 31 16 0 11 May 2022
Safe Reinforcement Learning Using Black-Box Reachability Analysis Mahmoud Selim Amr Alanwar Shreyas Kousik Grace Gao Marco Pavone Karl H. Johansson 29 32 0 15 Apr 2022
Towards Painless Policy Optimization for Constrained MDPs Arushi Jain Sharan Vaswani Reza Babanezhad Csaba Szepesvári Doina Precup 22 7 0 11 Apr 2022
Safe Reinforcement Learning for Legged Locomotion Tsung-Yen Yang Tingnan Zhang Linda Luu Sehoon Ha Jie Tan Wenhao Yu 29 40 0 05 Mar 2022
Model-free Neural Lyapunov Control for Safe Robot Navigation Zikang Xiong Joe Eappen A. H. Qureshi Suresh Jagannathan 32 8 0 02 Mar 2022
Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods Charles Dawson Sicun Gao Chuchu Fan 46 232 0 23 Feb 2022
Learning Neural Networks under Input-Output Specifications Z. Abdeen He Yin V. Kekatos Ming Jin 21 8 0 23 Feb 2022
Accelerating Primal-dual Methods for Regularized Markov Decision Processes Haoya Li Hsiang-Fu Yu Lexing Ying Inderjit Dhillon 36 4 0 21 Feb 2022
Learning a Shield from Catastrophic Action Effects: Never Repeat the Same Mistake Shahaf S. Shperberg Bo Liu Peter Stone 34 7 0 19 Feb 2022
CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning Long Yang Jiaming Ji Juntao Dai Yu Zhang Pengfei Li Gang Pan 12 17 0 15 Feb 2022
MuZero with Self-competition for Rate Control in VP9 Video Compression Amol Mandhane A. Zhernov Maribeth Rauh Chenjie Gu Miaosen Wang ... Jackson Broshear Julian Schrittwieser Thomas Hubert Oriol Vinyals Timothy A. Mann 37 44 0 14 Feb 2022
Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation Aivar Sootla Alexander I. Cowen-Rivers Taher Jafferjee Ziyan Wang D. Mguni Jun Wang Haitham Bou-Ammar 34 54 0 14 Feb 2022
SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition Dylan Slack Yinlam Chow Bo Dai Nevan Wichers OffRL 37 7 0 10 Feb 2022
LyaNet: A Lyapunov Framework for Training Neural ODEs I. D. Rodriguez Aaron D. Ames Yisong Yue 35 51 0 05 Feb 2022
Towards Safe Reinforcement Learning with a Safety Editor Policy Haonan Yu Wei Xu Haichao Zhang OffRL 69 31 0 28 Jan 2022
Constrained Variational Policy Optimization for Safe Reinforcement Learning Zuxin Liu Zhepeng Cen Vladislav Isenbaev Wei Liu Zhiwei Steven Wu Bo Li Ding Zhao 27 76 0 28 Jan 2022