Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory
暂无分享,去创建一个
Bin Hu | Usman Ahmed Syed | B. Hu | U. Syed
[1] João Pedro Hespanha,et al. Linear Systems Theory , 2009 .
[2] H. Kushner,et al. Stochastic Approximation and Recursive Algorithms and Applications , 2003 .
[3] Thinh T. Doan,et al. Performance of Q-learning with Linear Function Approximation: Stability and Finite-Time Analysis , 2019 .
[4] R. Srikant,et al. Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning , 2019, COLT.
[5] Mihailo R. Jovanovic,et al. The Proximal Augmented Lagrangian Method for Nonsmooth Composite Optimization , 2016, IEEE Transactions on Automatic Control.
[6] Bin Hu,et al. Dissipativity Theory for Nesterov's Accelerated Method , 2017, ICML.
[7] John N. Tsitsiklis,et al. Analysis of temporal-difference learning with function approximation , 1996, NIPS 1996.
[8] M. Overton,et al. On the Lidskii-Vishik-Lyusternik Perturbation Theory for Eigenvalues of Matrices with Arbitrary Jordan Structure , 1997, SIAM J. Matrix Anal. Appl..
[9] Chi-Tsong Chen,et al. Linear System Theory and Design , 1995 .
[10] Raja Sengupta,et al. A bounded real lemma for jump systems , 2003, IEEE Trans. Autom. Control..
[11] Shalabh Bhatnagar,et al. Fast gradient-descent methods for temporal-difference learning with linear function approximation , 2009, ICML '09.
[12] Asuman E. Ozdaglar,et al. A Universally Optimal Multistage Accelerated Stochastic Gradient Method , 2019, NeurIPS.
[13] Peter Seiler,et al. Direct Synthesis of Iterative Algorithms With Bounds on Achievable Worst-Case Convergence Rate , 2019, 2020 American Control Conference (ACC).
[14] Tosio Kato. Perturbation theory for linear operators , 1966 .
[15] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.
[16] Bin Hu,et al. Control interpretations for first-order optimization methods , 2017, 2017 American Control Conference (ACC).
[17] Bin Hu,et al. Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs , 2018, ICML.
[18] L. Ghaoui,et al. Robust state-feedback stabilization of jump linear systems , 1996 .
[19] Richard S. Sutton,et al. Learning to predict by the methods of temporal differences , 1988, Machine Learning.
[20] R. Sutton,et al. A convergent O ( n ) algorithm for off-policy temporal-difference learning with linear function approximation , 2008, NIPS 2008.
[21] Benjamin Recht,et al. Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints , 2014, SIAM J. Optim..
[22] John N. Tsitsiklis,et al. Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.
[23] Necdet Serhat Aybat,et al. Robust Accelerated Gradient Method , 2018 .
[24] Peter Seiler,et al. A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints , 2017, COLT.
[25] V. Borkar. Stochastic Approximation: A Dynamical Systems Viewpoint , 2008 .
[26] R. P. Marques,et al. Discrete-Time Markov Jump Linear Systems , 2004, IEEE Transactions on Automatic Control.
[27] Jan Peters,et al. Policy evaluation with temporal differences: a survey and comparison , 2015, J. Mach. Learn. Res..
[28] Bin Hu,et al. Robust convergence analysis of distributed optimization algorithms , 2017, 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton).
[29] Bin Hu,et al. A Robust Accelerated Optimization Algorithm for Strongly Convex Functions , 2017, 2018 Annual American Control Conference (ACC).
[30] Hisham Abou-Kandil,et al. On the solution of discrete-time Markovian jump linear quadratic control problems , 1995, Autom..
[31] Yuguang Fang,et al. Stochastic stability of jump linear systems , 2002, IEEE Trans. Autom. Control..
[32] Marek Petrik,et al. Finite-Sample Analysis of Proximal Gradient TD Algorithms , 2015, UAI.
[33] Enrique Mallada,et al. An integral quadratic constraint framework for real-time steady-state optimization of linear time-invariant systems , 2018, 2018 Annual American Control Conference (ACC).
[34] A. Willsky,et al. Discrete-time Markovian-jump linear quadratic optimal control , 1986 .
[35] K. Loparo,et al. Stochastic stability properties of jump linear systems , 1992 .
[36] Shuo Han,et al. Systematic Design of Decentralized Algorithms for Consensus Optimization , 2019, IEEE Control Systems Letters.
[37] L. A. Prashanth,et al. Stochastic Recursive Algorithms for Optimization: Simultaneous Perturbation Methods , 2012 .
[38] H. Chizeck,et al. Controllability, observability and discrete-time markovian jump linear quadratic control , 1988 .
[39] Manuel Kindelan,et al. Laurent expansion of the inverse of perturbed, singular matrices , 2015, J. Comput. Phys..
[40] R. Srikant,et al. Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning , 2019, NeurIPS.
[41] Csaba Szepesvári,et al. Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go? , 2018, AISTATS.
[42] Alejandro Ribeiro,et al. Analysis of Optimization Algorithms via Integral Quadratic Constraints: Nonstrongly Convex Problems , 2017, SIAM J. Optim..
[43] Yingbin Liang,et al. Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples , 2019, NeurIPS.
[44] Shie Mannor,et al. Finite Sample Analyses for TD(0) With Function Approximation , 2017, AAAI.
[45] M. Fragoso,et al. Stability Results for Discrete-Time Linear Systems with Markovian Jumping Parameters , 1993 .
[46] Jalaj Bhandari,et al. A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation , 2018, COLT.
[47] Randy A. Freeman,et al. The Fastest Known Globally Convergent First-Order Method for Minimizing Strongly Convex Functions , 2018, IEEE Control Systems Letters.
[48] Konstantin Avrachenkov,et al. Analytic perturbation of generalized inverses , 2013 .
[49] Alejandro Ribeiro,et al. A dynamical systems perspective to convergence rate analysis of proximal algorithms , 2017, 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton).
[50] Donghwan Lee,et al. Target-Based Temporal Difference Learning , 2019, ICML.
[51] Georgios B. Giannakis,et al. A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation , 2019, ArXiv.