A kernel based true online Sarsa(λ) for continuous space control problems
نویسندگان
چکیده
منابع مشابه
Reproducing Kernel Space Hilbert Method for Solving Generalized Burgers Equation
In this paper, we present a new method for solving Reproducing Kernel Space (RKS) theory, and iterative algorithm for solving Generalized Burgers Equation (GBE) is presented. The analytical solution is shown in a series in a RKS, and the approximate solution u(x,t) is constructed by truncating the series. The convergence of u(x,t) to the analytical solution is also proved.
متن کاملBounded Kernel-Based Online Learning
A common problem of kernel-based online algorithms, such as the kernel-based Perceptron algorithm, is the amount of memory required to store the online hypothesis, which may increase without bound as the algorithm progresses. Furthermore, the computational load of such algorithms grows linearly with the amount of memory used to store the hypothesis. To attack these problems, most previous work ...
متن کاملA Continuous Feedback Optimal Control based on Second-Variations for Problems with Control Constraints
The paper describes a continuous second-variation algorithm to solve optimal control problems where the control is defined on a closed set. A second order expansion of a Lagrangian provides linear updates of the control to construct a locally feedback optimal control of the problem. Since the process involves a backward and a forward stage, which require storing trajectories, a method has been ...
متن کاملReinforcement Learning for Continuous Stochastic Control Problems
This paper is concerned with the problem of Reinforcement Learning (RL) for continuous state space and time stocha.stic control problems. We state the Harnilton-Jacobi-Bellman equation satisfied by the value function and use a Finite-Difference method for designing a convergent approximation scheme. Then we propose a RL algorithm based on this scheme and prove its convergence to the optimal sol...
متن کاملA Method for Solving Optimal Control Problems Using Genetic Programming
This paper deals with a novel method for solving optimal control problems based on genetic programming. This approach produces some trial solutions and seeks the best of them. If the solution cannot be expressed in a closed analytical form then our method produces an approximation with a controlled level of accuracy. Using numerical examples, we will demonstrate how to use the results.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer Science and Information Systems
سال: 2017
ISSN: 1820-0214,2406-1018
DOI: 10.2298/csis170107029z