A one-measurement form of simultaneous perturbation stochastic approximation
From MaRDI portal
Publication:674970
DOI10.1016/S0005-1098(96)00149-5zbMath0867.93086OpenAlexW2012117977MaRDI QIDQ674970
Publication date: 7 August 1997
Published in: Automatica (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/s0005-1098(96)00149-5
Related Items (30)
On stochastic extremum seeking via adaptive perturbation-demodulation loop ⋮ Multiscale Q-learning with linear function approximation ⋮ Online estimation of hazard rate under random censoring ⋮ Sampled-data extremum-seeking framework for constrained optimization of nonlinear dynamical systems ⋮ Actor-critic algorithms for hierarchical Markov decision processes ⋮ Reinforcement learning based algorithms for average cost Markov decision processes ⋮ The multivariate Révész's online estimator of a regression function and its averaging ⋮ Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning ⋮ Simultaneous perturbation stochastic approximation: towards one-measurement per iteration ⋮ Variance-constrained actor-critic algorithms for discounted and average reward MDPs ⋮ Three-string inharmonic networks ⋮ No-regret learning for repeated non-cooperative games with lossy bandits ⋮ New algorithms of the Q-learning type ⋮ Designing inharmonic strings ⋮ Online estimation of integrated squared density derivatives ⋮ Accelerated randomized stochastic optimization. ⋮ A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm ⋮ A randomized stochastic optimization algorithm: its estimation accuracy ⋮ Fuzzy age-dependent replacement policy and SPSA algorithm based-on fuzzy simulation ⋮ A compact law of the iterated logarithm for online estimator of hazard rate under random censoring ⋮ Simultaneous perturbation Newton algorithms for simulation optimization ⋮ An alternating variable method with varying replications for simulation response optimization ⋮ Recursive estimators of integrated squared density derivatives ⋮ Simultaneous Perturbation Stochastic Approximation with Norm-Limited Update Vector ⋮ Stochastic approximation search algorithms with randomization at the input ⋮ The stochastic approximation method for the estimation of a multivariate probability density ⋮ Revisiting the ODE method for recursive algorithms: fast convergence using quasi stochastic approximation ⋮ Stochastic relaxed inertial forward-backward-forward splitting for monotone inclusions in Hilbert spaces ⋮ Derivative-free optimization over multi-user MIMO networks ⋮ Simulation response optimization via direct conjugate direction method
Cites Work
- Constrained optimization via stochastic approximation with a simultaneous perturbation gradient approximation
- On the use of an SPSA-based model-free controller in quality improvement
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Acceleration of Stochastic Approximation by Averaging
- On Asymptotic Normality in Stochastic Approximation
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication: A one-measurement form of simultaneous perturbation stochastic approximation
