Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 17 of 17 for “"Linear Function Approximation"”.

  1. Applications of fuzzy counterpropagation neural networks to non-linear function approximation and background noise elimination

    … fuzzy set approach and which can perform a non-linear function approximation. The model is used as the basic structure of an adaptive filter. The learning capability of ANN is expected to be able to reduce the development time and cost of the designing adaptive filters based on fuzzy set …

    edithcowan Repository record for Applications of fuzzy counterpropagation neural networks to non-linear function approximation and background noise elimination (opens in a new tab)

  2. Reinforcement Learning with Finite Time and Sample Guarantees

    … dimensionality of the state/action space, function approximators have been utilized in reinforcement learning algorithms, such as deep reinforcement learning. Nevertheless, the efficacy of these advanced algorithms frequently does not match that observed in tabular frameworks, even when …

    tamu Repository record for Reinforcement Learning with Finite Time and Sample Guarantees (opens in a new tab)

  3. A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms

    … are presented in Chapter 1. Part I: Stochastic Approximation. The main body of this thesis is divided into three parts. In the first part of the thesis, we focus on studying the stochastic approximation method. Stochastic approximation is the major workhorse for large-scale optimization and …

    gatech Repository record for A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms (opens in a new tab)

  4. Analysis of centralized and distributed temporal difference learning

    Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. This thesis provides an interpretation of this method in terms of a splitting of the gradient of an …

    bu Repository record for Analysis of centralized and distributed temporal difference learning (opens in a new tab)

  5. Finite-sample Guarantees of Stochastic Approximation Algorithms in Average-reward Reinforcement Learning and Decentralized Stochastic Optimization

    … the finite-sample guarantees of stochastic approximation (SA) algorithms, which are central to solving root-finding and fixed-point problems in optimization and reinforcement learning (RL). We first provide the finite-sample guarantees for average-reward TD($\lambda$) with linear function …

    gatech Repository record for Finite-sample Guarantees of Stochastic Approximation Algorithms in Average-reward Reinforcement Learning and Decentralized Stochastic Optimization (opens in a new tab)

  6. Splitting Gaussian Densities to Minimize Variance Along a Direction of Nonlinearity

    Nonlinear functions of random vectors are frequently used in signal processing, and especially in state space tracking algorithms. Many of these algorithms require a way of estimating the probability density of the state vector at the output of the nonlinear function. Algorithms derived from Kalman …

    portland-state Repository record for Splitting Gaussian Densities to Minimize Variance Along a Direction of Nonlinearity (opens in a new tab)

  7. Energy management in wireless communications : from convex optimization to machine learning

    … than the benchmarks. The proposed linear function approximation based decentralized \emph{Q}-learning converges as fast as the tabular \emph{Q}-learning while retaining robustness to the large state and action spaces. Based on Lyapunov learning algorithms, we can successfully …

    ubc Repository record for Energy management in wireless communications : from convex optimization to machine learning (opens in a new tab) Download PDF for Energy management in wireless communications : from convex optimization to machine learning (opens in a new tab)

  8. Learning Probabilistic Generative Models For Fast Sampling-Based Planning

    … we suggest a sampling method with a learned Q-function with linear function approximation based on feature representations such as Radial Basis Functions. This sampling method chooses the optimal node from which to extend the search tree via the softmax function of learned state values. We also …

    penn Repository record for Learning Probabilistic Generative Models For Fast Sampling-Based Planning (opens in a new tab)

  9. LEARNING ALGORITHMS FOR MARKOV DECISION PROCESSES

    … convergence result of a very general stochastic approximation algorithm to the case when the underlying Markov process exhibits periodicity. This result is used to extend the proof of convergence of Temporal Difference (TD) reinforcement learning schemes with linear function approximation for …

    maryland Repository record for LEARNING ALGORITHMS FOR MARKOV DECISION PROCESSES (opens in a new tab)

  10. A new solution for Markov Decision Processes and its aerospace applications

    … beenmitigated by various means, but primarily by approximation (under the umbrella of ApproximateDynamic Programmming) where the solution of the MDP (the value function) is modelled via anapproximation function. Many linear function approximation methods have been proposed sinceMarkov Decision …

    iastate Repository record for A new solution for Markov Decision Processes and its aerospace applications (opens in a new tab)

  11. Radar Spectrum Sharing with Reactive Emitters using Reinforcement Learning

    … access decisions in the discrete MDP model and a linear function approximation algorithm using the deterministic policy gradient theorem is used in the continuous MDP model. Simulations for both MDP models include a variety of time-varying and reactive emitters and alternative radar spectrum …

    gatech Repository record for Radar Spectrum Sharing with Reactive Emitters using Reinforcement Learning (opens in a new tab)

  12. Reinforcement learning for multi-agent and robust control systems

    … and establish their convergence guarantees when linear function approximation is used. Setting ii corresponds to a classical robust control problem, with linear dynamics and robustness concerns in the H∞-norm sense. In contrast to existing solvers, we introduce policy-gradient methods to solve …

    uiuc Repository record for Reinforcement learning for multi-agent and robust control systems (opens in a new tab)

  13. New Accelerated Methods for Optimization and Reinforcement Learning

    … first-order algorithms for large-scale nonlinear and stochastic optimization, addressing key challenges such as stochasticity, nonconvexity, and uncertainty in problem structures and parameters. We also develop new accelerated methods for reinforcement learning, accompanied by improved …

    gatech Repository record for New Accelerated Methods for Optimization and Reinforcement Learning (opens in a new tab)

  14. A Comparison of the Performance of Neural Q-learning and Soar-RL on a Derivative of the Block Design (BD)/Block Design Multiple Choice (BDMC) Subtests on the WISC-IV Intelligence Test

    Teaching an autonomous agent to perform tasks that are simple to humans can be complex, especially when the task requires successive steps, has a low likelihood of successful completion with a brute force approach, and when the solution space is too large or too complex to be explicitly encoded. …

    clemson Repository record for A Comparison of the Performance of Neural Q-learning and Soar-RL on a Derivative of the Block Design (BD)/Block Design Multiple Choice (BDMC) Subtests on the WISC-IV Intelligence Test (opens in a new tab)

  15. Fast and Reliable Optimization for Dynamic Decision-making Under Uncertainty

    … Chapter 2 introduces a new advantage gap function for these problems. This gap function provides close approximations of the (unknown) optimality gap, which can be easily estimated in a data-driven manner for RL. Moreover, by incorporating the gap function into the design of step size …

    gatech Repository record for Fast and Reliable Optimization for Dynamic Decision-making Under Uncertainty (opens in a new tab)

  16. Performance evaluation of measurement algorithms used in IEDs.

    … fault detection and execute various protection functions. The first and essential mathematical algorithm of any IED is the measurement algorithm. The aim of the measurement algorithm is to estimate the fundamental frequency component (phasor) of input current and voltage signals. Most protection …

    adelaide Repository record for Performance evaluation of measurement algorithms used in IEDs. (opens in a new tab)

  17. Applications of time-series generative models and inference techniques

    … contexts has usually required a rigid set of linearity constraints or assumptions about the distributions used for modelling. Furthermore, inference in non-linear models can be very difficult to scale to high-dimensional models. In recent years, deep learning has been a key innovation in …

    oxford Repository record for Applications of time-series generative models and inference techniques (opens in a new tab)