Learning multi-modal control programs

Authors:
Tejas R. Mehta;Magnus Egerstedt
Affiliations:
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA;School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA
Venue:
HSCC'05 Proceedings of the 8th international conference on Hybrid Systems: computation and control
Year:
2005

Citing 5
Cited 1

Asynchronous Stochastic Approximation and Q-Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
On the convergence of stochastic iterative dynamic programming algorithms

Neural Computation
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Model checking LTL over controllable linear systems is decidable

HSCC'03 Proceedings of the 6th international conference on Hybrid systems: computation and control

Comparing apples and oranges through partial orders: an empirical approach

ACC'09 Proceedings of the 2009 conference on American Control Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-modal control is a commonly used design tool for breaking up complex control tasks into sequences of simpler tasks. In this paper, we show that by viewing the control space as a set of such tokenized instructions rather than as real-valued signals, reinforcement learning becomes applicable to continuous-time control systems. In fact, we show how a combination of state-space exploration and multi-modal control converts the original system into a finite state machine, on which Q-learning can be utilized.