Affordable Access

Temporal-Difference Networks for Dynamical Systems with Continuous Observations and Actions

Authors
  • Vigorito, Christopher M.
Type
Preprint
Publication Date
May 09, 2012
Submission Date
May 09, 2012
Identifiers
arXiv ID: 1205.2608
Source
arXiv
License
Yellow
External links

Abstract

Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm for learning TD network representations of dynamical systems with continuous observations and actions. Our results show that the algorithm is capable of learning accurate and robust models of several noisy continuous dynamical systems. The algorithm presented here is the first fully incremental method for learning a predictive representation of a continuous dynamical system.

Report this publication

Statistics

Seen <100 times