Fetching the paper…
Reading the bibliography…
Safely exploring an unknown dynamical system is critical to the deployment of reinforcement learning (RL) in physical systems where failures may have catastrophic consequences.
Numerical identification of linear dynamic systems from normal operating records
Karl-Johan Åström and Torsten Bohlin · 1967
Earlier work this paper cites.
Recursive state estimation: Unknown but bounded errors and system inputs
Fred C. Schweppe · 1968
Earlier work this paper cites.
Sets of possible states of linear systems given perturbed observations
Hans S. Witsenhausen · 1968
Earlier work this paper cites.
System identification: A survey
Karl-Johan Åström and Pieter Eykhoff · 1971
Earlier work this paper cites.
The Stability and Control of Discrete Processes
Joseph P. LaSelle, editor · 1986
Earlier work this paper cites.
Non-linear system identification using neural networks
S. Chen, Billings S. A., and P. M. Grant · 1990
Earlier work this paper cites.
Estimation of parameter bounds from bounded-error data: a survey
Eric Walter and Hélène Piet-Lahanier · 1990
Earlier work this paper cites.
The componentwise distance to the nearest singular matrix
James Demmel · 1992
Earlier work this paper cites.
Optimal estimation theory for dynamic systems with set membership uncertainty: An overview
Mario Milanese and Antonio Vicino · 1996
Earlier work this paper cites.
System Identification: Theory for the User (2nd Edition)
Lennart Ljung, editor · 1999
Earlier work this paper cites.
Functional Analysis
Peter D. Lax, editor · 2002
Cited alongside, same era.
Robust dynamic programming
G. Iyengar · 2005
Cited alongside, same era.
Robust control of Markov decision processes with uncertain transition matrices
Arnab Nilim and Laurent El Ghaoui · 2005
Cited alongside, same era.
Neuroevolutionary reinforcement learning for generalized control of simulated helicopters
Rogier Koppejan and Shimon Whiteson · 2011
Cited alongside, same era.
Safe exploration of state and action spaces in reinforcement learning
Javier García and Fernando Fernández · 2012
Cited alongside, same era.
Safe exploration in Markov decision processes
Teodor Mihai Moldovan and Pieter Abbeel · 2012
Cited alongside, same era.
Safe and robust learning control with Gaussian processes
Felix Berkenkamp and Angela P. Schoellig · 2015
Later among the works it cites.
Time Series Analysis: Forecasting and Control (5th Edition)
George E. P. Box, Gwilym Jenkins, Gregory C. Reinsel, and Greta M. Ljung · 2015
Later among the works it cites.
A comprehensive survey on safe reinforcement learning
Javier García and Fernando Fernández · 2015
Later among the works it cites.
Safe exploration for optimization with Gaussian processes
Yanan Sui, Alkis Gotovos, Joel W. Burdick, and Andreas Krause · 2015
Later among the works it cites.
Concrete problems in AI safety
Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Mané · 2016
Later among the works it cites.
Safe policy improvement by minimizing robust baseline regret
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
System Identification: A Frequency Domain Approach (2nd Edition)
Rik Pintelon and Johan Schoukens, editors · 2012
Cited alongside, same era.
Machine learning applications for data center optimization
Jim Gao · 2014
Cited alongside, same era.
Reachability-based safe learning with Gaussian processes
Anayo K. Akametalu, Shahab Kaynama, Jaime Fisac, Melaine N. Zeilinger, Jeremy H. Gillula, and Claire J. Tomlin · 2014
Cited alongside, same era.
Safe exploration techniques for reinforcement learning – an overview
Martin Pecka and Tomas Svoboda · 2014
Cited alongside, same era.
Mohammad Ghavamzadeh, Marek Petrik, and Yinlam Chow · 2016
Later among the works it cites.
Safe exploration in finite Markov decision processes with Gaussian processes
Matteo Turchetta, Felix Berkenkamp, and Andreas Krause · 2016
Later among the works it cites.
Safe model-based reinforcement learning with stability guarantees
Matteo Turchetta, Felix Berkenkamp, Angela P. Schoellig, and Andreas Krause · 2017
Closest in time.
Econometric Analysis (8th Edition)
William H. Greene, editor · 2018
Closest in time.