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"

36 / 286 papers shown

Title
Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach Subin Huh Insoon Yang 6 20 0 24 Feb 2020
Conservative Exploration in Reinforcement Learning Evrard Garcelon Mohammad Ghavamzadeh A. Lazaric Matteo Pirotta 27 28 0 08 Feb 2020
Constrained Upper Confidence Reinforcement Learning Liyuan Zheng Lillian J. Ratliff 36 67 0 26 Jan 2020
Learning Stable Deep Dynamics Models Gaurav Manek J. Zico Kolter 35 191 0 17 Jan 2020
Learning for Safety-Critical Control with Control Barrier Functions Andrew J. Taylor Andrew W. Singletary Yisong Yue Aaron D. Ames 21 237 0 20 Dec 2019
Safe Interactive Model-Based Learning Marco Gallieri Seyed Sina Mirrazavi Salehian N. E. Toklu A. Quaglino Jonathan Masci Jan Koutník Faustino J. Gomez 12 12 0 15 Nov 2019
Convergent Policy Optimization for Safe Reinforcement Learning Ming Yu Zhuoran Yang Mladen Kolar Zhaoran Wang 16 91 0 26 Oct 2019
IPO: Interior-point Policy Optimization under Constraints Yongshuai Liu J. Ding Xin Liu 24 176 0 21 Oct 2019
CAQL: Continuous Action Q-Learning Moonkyung Ryu Yinlam Chow Ross Anderson Christian Tjandraatmadja Craig Boutilier 197 42 0 26 Sep 2019
Reconnaissance and Planning algorithm for constrained MDP S. Maeda Hayato Watahiki Shintarou Okada Masanori Koyama 9 2 0 20 Sep 2019
Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation Yuh-Shyang Wang Tsui-Wei Weng Luca Daniel AAML 29 16 0 18 Aug 2019
Neural Simplex Architecture Dung Phan Radu Grosu N. Jansen Nicola Paoletti S. Smolka Scott D. Stoller 24 61 0 01 Aug 2019
Let's Keep It Safe: Designing User Interfaces that Allow Everyone to Contribute to AI Safety Travis Mandel Jahnu Best Randall H. Tanaka Hiram Temple Chansen Haili Kayla Schlechtinger Roy Szeto 13 1 0 09 Jul 2019
A Scheme for Dynamic Risk-Sensitive Sequential Decision Making Shuai Ma Jia Yuan Yu A. S. Satir 11 1 0 09 Jul 2019
Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation Ankush Chakrabarty Devesh K. Jha G. Buzzard Yebin Wang K. Vamvoudakis 14 25 0 03 Jul 2019
Provably Efficient Q-Learning with Low Switching Cost Yu Bai Tengyang Xie Nan Jiang Yu Wang 11 92 0 30 May 2019
Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework M. Nazari Majid Jahani L. Snyder Martin Takáč OffRL OnRL 21 1 0 30 May 2019
Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding Osbert Bastani 16 9 0 25 May 2019
Control Regularization for Reduced Variance Reinforcement Learning Richard Cheng Abhinav Verma G. Orosz Swarat Chaudhuri Yisong Yue J. W. Burdick OffRL 20 76 0 14 May 2019
Smoothing Policies and Safe Policy Gradients Matteo Papini Matteo Pirotta Marcello Restelli 32 29 0 08 May 2019
An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments Andrea V. Bajcsy Somil Bansal Eli Bronstein Varun Tolani Claire Tomlin 17 88 0 01 May 2019
Challenges of Real-World Reinforcement Learning Gabriel Dulac-Arnold D. Mankowitz Todd Hester OffRL 37 543 0 29 Apr 2019
End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks Richard Cheng G. Orosz R. Murray J. W. Burdick 17 607 0 21 Mar 2019
Safety-Guided Deep Reinforcement Learning via Online Gaussian Process Estimation Jiameng Fan Wenchao Li OffRL OnRL GP 16 18 0 06 Mar 2019
Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems Andrew J. Taylor Victor D. Dorobantu Hoang Minh Le Yisong Yue Aaron D. Ames 117 78 0 04 Mar 2019
Conservative Agency via Attainable Utility Preservation Alexander Matt Turner Dylan Hadfield-Menell Prasad Tadepalli 30 49 0 26 Feb 2019
Network Offloading Policies for Cloud Robotics: a Learning-based Approach Sandeep P. Chinchali Apoorva Sharma James Harrison Amine Elhafsi Daniel Kang Evgenya Pergament Eyal Cidon Sachin Katti Marco Pavone OffRL 11 105 0 15 Feb 2019
Lyapunov-based Safe Policy Optimization for Continuous Control Yinlam Chow Ofir Nachum Aleksandra Faust Edgar A. Duénez-Guzmán Mohammad Ghavamzadeh 33 244 0 28 Jan 2019
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures Junhui Yin Jiayan Qiu Csaba Szepesvári Siqing Zhang Avraham Ruderman Jiyang Xie Krishnamurthy Dvijotham Zhanyu Ma N. Heess Pushmeet Kohli AAML 15 80 0 04 Dec 2018
Deep Reinforcement Learning Yuxi Li VLM OffRL 28 144 0 15 Oct 2018
Safely Learning to Control the Constrained Linear Quadratic Regulator Sarah Dean Stephen Tu Nikolai Matni Benjamin Recht 13 138 0 26 Sep 2018
Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guarantees Christopher Iliffe Sprague Petter Ögren 15 25 0 26 Sep 2018
Better Safe than Sorry: Evidence Accumulation Allows for Safe Reinforcement Learning Akshat Agarwal Abhinau K. Venkataramanan Kyle Dunovan Erik J Peterson Timothy D. Verstynen Katia Sycara OffRL 16 3 0 24 Sep 2018
Safe Reinforcement Learning via Probabilistic Shields N. Jansen Bettina Könighofer Sebastian Junges A. Serban Roderick Bloem 20 9 0 16 Jul 2018
First-order Methods Almost Always Avoid Saddle Points Jason D. Lee Ioannis Panageas Georgios Piliouras Max Simchowitz Michael I. Jordan Benjamin Recht ODL 95 83 0 20 Oct 2017
Safe Exploration in Markov Decision Processes T. Moldovan Pieter Abbeel 78 308 0 22 May 2012