Revisiting the ODE method for recursive algorithms: fast convergence using quasi stochastic approximation
From MaRDI portal
Publication:2070010
DOI10.1007/s11424-021-1251-5OpenAlexW3211240378MaRDI QIDQ2070010
Shuhang Chen, Adithya Devraj, Andrey Berstein, Sean P. Meyn
Publication date: 21 January 2022
Published in: Journal of Systems Science and Complexity (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s11424-021-1251-5
stochastic approximationreinforcement learninglearning and adaptive systems in artificial intelligence
Cites Work
- Unnamed Item
- Stochastic averaging and stochastic extremum seeking
- A one-measurement form of simultaneous perturbation stochastic approximation
- Stochastic approximation. A dynamical systems viewpoint.
- Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissant
- New method of stochastic approximation type
- Identification and stochastic adaptive control
- Asynchronous stochastic approximation and Q-learning
- Simple statistical gradient-following algorithms for connectionist reinforcement learning
- Random gradient-free minimization of convex functions
- Adaption and learning in automatic systems. Translated by Z. J. Nikolic
- Stochastic simulation: Algorithms and analysis
- How much uncertainty can be dealt with by feedback?
- Stochastic approximation with averaging innovation applied to Finance
- Adaptive control of Markov chains, I: Finite parameter set
- Adaptive control for time-varying systems: A combination of Martingale and Markov chain techniques
- Sequences with low discrepancy generalisation and application to bobbins-monbo algorithm
- Estimating time-varying parameters by the Kalman filter based algorithm: stability and convergence
- Convergence rate of least-squares identification and adaptive control for stochastic systems†
- A new approach to stochastic adaptive control
- Identification and Adaptive Control of Markov Chains
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Acceleration of Stochastic Approximation by Averaging
- Random-seeking methods for the stochastic unconstrained optimization
- Analysis of recursive stochastic algorithms
- Stability of Recursive Stochastic Tracking Algorithms
- On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
- Introduction to Stochastic Search and Optimization
- Real‐Time Optimization by Extremum‐Seeking Control
- A Kiefer-Wolfowitz algorithm with randomized differences
- THE HEAVY BALL WITH FRICTION METHOD, I. THE CONTINUOUS DYNAMICAL SYSTEM: GLOBAL EXPLORATION OF THE LOCAL MINIMA OF A REAL-VALUED FUNCTION BY ASYMPTOTIC ANALYSIS OF A DISSIPATIVE DYNAMICAL SYSTEM
- Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences
- A variational perspective on accelerated methods in optimization
- Estimation and control in Markov chains
- Performance analysis of general tracking algorithms
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
- Control Systems and Reinforcement Learning
- Stability of Stochastic Approximations With “Controlled Markov” Noise and Temporal Difference Learning
- Stochastic Estimation of the Maximum of a Regression Function
- A Stochastic Approximation Method
