Search
Now showing items 1-5 of 5
Approximate Dynamic Programming for Two-player Zero-sum Game Related to H∞ Control of Unknown Nonlinear Continuous-time Systems
Year: 2015
Abstract:
This paper develops a novel concurrent learning-based approximate dynamics programming (ADP) algorithm for solving the two-player zero-sum (ZS) game arising in H∞ control of continuous-time (CT) systems with unknown nonlinear ...
Online Concurrent Reinforcement Learning Algorithm to Solve Two-player Zero-sum Games for Partially-unknown Nonlinear Continuous-time Systems
Year: 2014
Abstract:
the need for persistence of excitation condition is relaxed by using the idea of concurrent learning. First, H1 control problem is formulated as a two-player zero-sum game, and then, online CRLA is employed to obtain the approximation of the optimal value...
Policy Iteration Algorithm Based on Experience Replay to Solve H∞ Control Problem of Partially Unknown Nonlinear Systems
Year: 2014
Abstract:
In this paper, an online adaptive optimal control algorithm based on policy iteration (PI) is developed to solve the H∞ control problem of partially unknown nonlinear continuous-time (CT) systems. The convergence of existing ...
Evaluation of the effectiveness of radar detection method for mine-like objects using seismic shocks
Publisher: IEEE
Year: 2014
The ALICE experience: A learning framework to promote gaming literacy for educators and its refinement
Publisher: IEEE
Year: 2014