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 87 for “"Policy Iteration"”.
-
Empirical convergence of the policy iteration algorithm for average optimal Markov decision processes
Includes bibliographical references.
-
Approximate Policy Iteration (API) with neural networks for the generalized single node energy storage problem
… hence approximate dynamic programming using policy iteration (API) is often employed in such cases. API does not always work, one reason being that the approximation architectures used are often linear for computational tractability reasons. We propose a mathematical model which allows easier …
-
On the Convergence of Three Applied Stochastic Models related to Reflected Jump Diffusions, Fast-Slow Dynamical Systems, and Optimistic Policy Iteration
… Lévy noise, and a variant of the Optimistic Policy Iteration algorithm in Reinforcement Learning. The connecting thread between all three projects is in showing convergence of these objects whose results have direct applied implications. A large deviation principle is established for general …
-
Numerical Methods for Pricing a Guaranteed Minimum Withdrawal Benefit (GMWB) as a Singular Control Problem
… discretized algebraic equations. The classic policy iteration approach works well for the Geometric Brownian Motion case. However it is not efficient in some circumstances such as when the underlying asset follows a Poisson jump diffusion process. We develop a combined fixed point policy …
-
Option Pricing under Regime Switching (Analytical, PDE, and FFT Methods)
… compare a number of iterative procedures (full policy iteration, fixed point-policy iteration, and local American iteration) for the associated nonlinear algebraic equations. Specifically, a linear system appears in the full policy iteration which can be solved directly or iteratively. Numerical …
-
Policy Optimization with f-Divergence Regularization
Policy iteration is a common algorithm framework in reinforcement learning (RL) to find the optimal policy for a Markov decision process (MDP). Previously, researchers have developed several policy iteration algorithms based on the Kullback–Leibler (KL) divergence. In this thesis, we extend …
-
Acceleration of Iterative Methods for Markov Decision Processes
… employed to solve MDP problems include value iteration and policy iteration. Although simple to implement, these approaches are, nevertheless, limited in the size of problems that can be solved, due to excessive computation required to find close-to-optimal solutions. My thesis proposes a new …
-
Exponential Lower Bounds for Solving Infinitary Payoff Games and Linear Programs
… can be solved in deterministic polynomial time. Policy iteration is one of the most important algorithmic schemes for solving infinitary payoff games. It is parameterized by an improvement rule that determines how to proceed in the iteration from one policy to the next. It is a major open problem …
-
User Equilibria in Systems of Parallel Processor Sharing Queues
… work exploring the structure of fixed points of policy iteration in the system with two queues. We confirm previous findings of complex behaviour arising from policy iteration in this system. In particular, we see that policy iteration is not guaranteed to converge to a fixed point, and may …
-
Computational methods for Markov decision problems
… the effort required to determine an optimal policy. We discuss the implementation of Porteus' scalar extrapolation methods in the modified policy iteration algorithm and show that the results using only a final scalar extrapolation will be the same as those obtained by applying scalar …
-
Texas Hold’em poker by LLM
… in-context learning Brown et al. (2020), and policy iteration Sutton and Barto (1998), we develop a method that can iteratively learn optimal poker strategies directly from game logs, without relying on expert demonstrations or gradient-based fine-tuning. The model uses in-context policy …
-
Multigrid Methods for Hamilton-Jacobi-Bellman and Hamilton-Jacobi-Bellman-Isaacs Equations
… as smoother for multigrid. In contrast with policy iteration, the relaxation scheme is convergent for both HJB and HJBI equations. We show by local Fourier analysis that the damped-relaxation smoother effectively reduces high frequency error. For problems where the control has jumps, …
-
Optimization of Policy Evaluation and Policy Improvement Methods in Portfolio Optimization using Quasi-Monte Carlo Methods
… explored in recent work is the estimation of policy gradients for reinforcement learning. They found that for many standard continuous control problems, the numerical methods randomized Quasi-Monte Carlo (RQMC) and Array-RQMC that used low-discrepancy point sets improved the efficiency of both …
-
Numerical schemes for stochastic hybrid control problems in finance
… of the penalized equations, and establish that policy iteration applied to the discrete equation is monotonically convergent with an arbitrary initial guess in an infinite dimensional setting. Numerical examples for infinite-horizon optimal switching problems are presented to illustrate that the …
-
Numerical solution of discretised HJB equations with applications in finance
… arising in American option pricing, we study a policy iteration method. We show, analytically and numerically, that, in standard situations, the computational cost of this approach is comparable to that of European option pricing. We also characterise the shortcomings of policy iteration, …
-
Trustworthy Reinforcement Learning under Constraints and Perturbations
… (DBCE) and the Density-Based Correlated Policy Iteration (DBCPI) algorithm. (2) To address sequential resource allocation with situational constraints, we develop a primal–dual Situational Constraint RL (SCRL) framework, introducing a density-based formulation to measure resource …
-
Approximate Dynamic Programming with Applications
… common methods for solving such equations are policy iteration and value iteration. Both these methods are studied in this thesis.An approximate policy iteration algorithm is presented for both the continuous and discrete time settings. It is shown that the sequence produced by this algorithm …
-
Learning-based Optimal Control of Time-Varying Linear Systems Over Large Time Intervals
… This allows the utilization of an off-policy iteration method to learn the controller gains. We show that the performance of the learning-based controller approximates that of the model-based optimal controller and the approximation accuracy improves as the control problem’s time …
-
Two essays on dynamic programming and reinforcement learning
… dynamic programming (DP) methods, i.e., value iteration and policy iteration, are commonly used to solve MDPs/SMDPs, value iteration is easier to apply than policy iteration. The existing value iteration algorithms for average reward SMDPs have some noteworthy limitations, which are sought to …
Page 1 of 5