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 20 of 26 for “"Finite - time convergence"”.

  1. FINITE-TIME CONVERGENCE ANALYSIS OF ACTOR-CRITIC ALGORITHMS

    … In the thesis, we provide the first global convergence guarantees for two-timescale actor-critic (AC) on linear quadratic regulator (LQR) problems, achieving epsilon-optimality with provable sample complexity. These results are generalized to Markov Decision Processes (MDPs) and extended to …

    nus Repository record for FINITE-TIME CONVERGENCE ANALYSIS OF ACTOR-CRITIC ALGORITHMS (opens in a new tab) Download file for FINITE-TIME CONVERGENCE ANALYSIS OF ACTOR-CRITIC ALGORITHMS (opens in a new tab)

  2. Asymptotic properties and finite time convergence of classical and modified methods for stochastic differential equations

    … Another main focus of numerical analysis is the finite time convergence. Our work on this topic is to modify the explicit Euler-Maruyama method and investigate the strong convergence (in the L2 sense) of it. Our investigation first goes to reproduce the asymptotic boundedness in small moment of …

    strathclyde Repository record for Asymptotic properties and finite time convergence of classical and modified methods for stochastic differential equations (opens in a new tab)

  3. Το νευρωνικό δίκτυο προσήμου για προβλήματα ελαχίστου χωρίς περιορισμούς

    … Filippov’s approach, we first prove asymptotic convergence of the Sign Neural Network. Also, finite-time convergence of the solutions is established and an improved upper bound for convergence time is given. A first contribution of this Thesis is a detailed calculation of Filippov’s set-valued …

    greece Repository record for Το νευρωνικό δίκτυο προσήμου για προβλήματα ελαχίστου χωρίς περιορισμούς (opens in a new tab)

  4. Uniform finite time stabilisation of non-smooth and variable structure systems with resets

    This thesis studies uniform finite time stabilisation of uncertain variable structure and non-smooth systems with resets. Control of unilaterally constrained systems is a challenging area that requires an understanding of the underlying mechanics that give rise to reset or jumps while synthesizing …

    kent Download PDF for Uniform finite time stabilisation of non-smooth and variable structure systems with resets (opens in a new tab)

  5. Invariance and Sliding Modes. Application to coordination of multi-agent systems, bioprocesses estimation, and control in living cells

    … the problem of stability analysis from that of finite-time convergence of the super-twisting sliding mode algorithm. A nonlinear change of coordinates and a time-scaling are used to provide simple, yet flexible design methods and stability proofs. Application of the method to the design of …

    upv Repository record for Invariance and Sliding Modes. Application to coordination of multi-agent systems, bioprocesses estimation, and control in living cells (opens in a new tab)

  6. Nonlinear sliding mode control of grid connected converters: design and stability analysis

    … to achieve enhanced robustness and faster finite time convergence. In the direct approach, a Higher Order Sliding Mode Control (HOSMC) strategy with embedded current control is formulated. The proposed HOSMC provides variable gain control and finite time convergence while eliminating the …

    manitoba Repository record for Nonlinear sliding mode control of grid connected converters: design and stability analysis (opens in a new tab)

  7. Quaternion Sliding Mode-based Backstepping control design for Quadrotors in the Presence of Unknown Uncertainties

    … to mitigate chattering issues and guarantee finite-time convergence, we propose Quaternion-based Adaptive Backstepping Control (ABC) and Adaptive Fast Terminal Sliding Mode Control (AFTSMC). A quaternion-based AFTSMC is proposed to overcome significant unknown time-varying uncertainties, …

    carleton Repository record for Quaternion Sliding Mode-based Backstepping control design for Quadrotors in the Presence of Unknown Uncertainties (opens in a new tab)

  8. Hybrid Observer Design for Bioreactors with Asynchronous Measurements

    … the modeling of the system where both continuous-time and discrete-time dynamics coexist. For linear systems, a hybrid observer is designed that utilizes a history of past measurements to achieve finite-time convergence. A relaxed variant is proposed to enhance robustness to measurement noise. For …

    queens Repository record for Hybrid Observer Design for Bioreactors with Asynchronous Measurements (opens in a new tab)

  9. Robust trajectory tracking of mobile manipulators based on extended state observer and nonlinear control

    … based nonlinear control strategies for real-time trajectory tracking of mobile manipulators (MMs) operating in uncertain and dynamic environments. The developed approaches aim to overcome the limitations of conventional control methods in handling nonlinear couplings, parameter uncertainties, …

    ets-quebec Download PDF for Robust trajectory tracking of mobile manipulators based on extended state observer and nonlinear control (opens in a new tab)

  10. Fixed-Time Reinforcement Learning-based Control for Safe Autonomy

    … existing safe learning architectures lack finite time convergence guarantees, rendering these algorithms impractical for real-world applications. In this dissertation, we enable safe autonomy by endowing autonomous systems with safety-critical control frameworks predicated on online …

    gatech Repository record for Fixed-Time Reinforcement Learning-based Control for Safe Autonomy (opens in a new tab)

  11. Terminal sliding mode control for rigid robotic manipulators with uncertain dynamics

    … uncertain parameter bounds. The law ensures finite time error convergence to the system origin and is simple to implement The second law treats the manipulator as a partially known system. The known dynamics are used to build a nominal control law and the effects of unknown system dynamics …

    edithcowan Repository record for Terminal sliding mode control for rigid robotic manipulators with uncertain dynamics (opens in a new tab)

  12. Monitoring strategies in adaptive sliding mode control and event-triggered extremum seeking

    … disturbances with unknown upper bounds. Finite-time convergence of the tracking error to a predefined neighborhood of the origin of the closed-loop system is proved with guaranteed transient and steady-state performance. The novelty of our result lies on two important adaptation tools: …

    brazil-uerj Repository record for Monitoring strategies in adaptive sliding mode control and event-triggered extremum seeking (opens in a new tab)

  13. Receding Horizon based Cooperative Vehicle Control with Optimal Task Allocation

    … mission space sequentially at a priori unknown time instants and a priori unknown locations, and then move on a priori unknown trajectories. A group of vehicles with known dynamics are employed to visit the targets as quickly and efficiently as possible. To this end, a time-discounting reward is …

    concordia Download PDF for Receding Horizon based Cooperative Vehicle Control with Optimal Task Allocation (opens in a new tab)

  14. A Dynamical Systems Perspective on Optimization Algorithms

    … \textbf{Part I (Ch 2 and 3): Continuous-Time and Discrete-Time Optimization} We investigate the relationship between continuous-time dynamical systems and traditional iterative optimization algorithms. By reinterpreting iterative methods like gradient descent as continuous-time systems …

    penn Repository record for A Dynamical Systems Perspective on Optimization Algorithms (opens in a new tab)

  15. Reinforcement Learning with Finite Time and Sample Guarantees

    … demonstrations and human feedback, establishing finite-sample guarantees for reward estimation. I first present a single-loop regularized Q-learning algorithm for minimizing the projected Bellman error with finite time convergence guarantees in the case of linear function approximation. The …

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

  16. Aircraft System Identification Approach for Control Surface Fault Diagnosis

    … aircraft. The work considers several real-time system identification methods to estimate changes in control effectiveness and provide fault information to a fault-tolerant control allocation framework. A baseline aero-propulsive model for an experimental aircraft was developed from …

    vt Repository record for Aircraft System Identification Approach for Control Surface Fault Diagnosis (opens in a new tab)

  17. Solving chaotic ODEs with time-parallel algorithms

    … of chaotic dynamical systems over long time spans, a core problem in fields such as fusion energy research, climate modelling, and fluid dynamics. Standard time-parallel algorithms work well for linear systems or over short time intervals, but perform poorly on long periods dominated by …

    oxford Repository record for Solving chaotic ODEs with time-parallel algorithms (opens in a new tab)

  18. Sample complexity of Reinforcement Learning algorithms with a focus on policy space methods

    … fast Reinforcement Learning algorithms with finite sample complexity guarantees. The work is divided into two main parts. In the first, we investigate stochastic approximation across various domains to establish finite sample complexity bounds. We study two settings: federated stochastic …

    gatech Repository record for Sample complexity of Reinforcement Learning algorithms with a focus on policy space methods (opens in a new tab)

  19. Προβλήματα σχεδιασμού ανάδρασης συστημάτων ελέγχου

    … error). The scheme guarantees exponential convergence of the state to zero in the L^{2} norm and a finite-time convergence of the parameter estimates to the true values of the unknown parameters. The scheme is developed for a specific benchmark problem with Dirichlet actuation, where the …

    greece Repository record for Προβλήματα σχεδιασμού ανάδρασης συστημάτων ελέγχου (opens in a new tab)

  20. Practical Issues in Formation Control of Multi-Robot Systems

    … involves two important considerations: (1) Real-time trajectory generation algorithms for distributed control based on nominal agent models, and (2) robust tracking of reference trajectories under model uncertainties. Proposed is a two-layer hierarchical architecture for collectivemotion control …

    tamu Repository record for Practical Issues in Formation Control of Multi-Robot Systems (opens in a new tab)

Page 1 of 2