A Planning Algorithm for Predictive State Representations
Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 1520-1520.
Abstract
We address the problem of optimally controlling stochastic environments that are partially observable. The standard method for tackling such problems is to define and solve a Partially Observable Markov Decision Process (POMDP). However, it is well known that exactly solving POMDPs is very costly computationally. Recently, Littman, Sutton and Singh (2002) have proposed an alternative representation of partially observable environments, called predictive state representations (PSRs). PSRs are grounded in the sequence of actions and observations of the agent, and hence relate the state representation directly to the agent's experience. In this paper, we present a policy iteration algorithm for finding policies using PSRs. In preliminary experiments, our algorithm produced good solutions.
@inproceedings{ijcai2003p258,
title = {A Planning Algorithm for Predictive State Representations},
author = {Izadi, Masoumeh T. and Precup, Doina},
booktitle = {Proceedings of the Eighteenth International Joint Conference on
Artificial Intelligence, {IJCAI-03}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Georg Gottlob},
pages = {1520--1520},
year = {2003},
url = {https://ijcai.org/proceedings/2003/258},
}
TY - CPAPER TI - A Planning Algorithm for Predictive State Representations AU - Izadi, Masoumeh T. AU - Precup, Doina T2 - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03 PB - International Joint Conferences on Artificial Intelligence PY - 2003 SP - 1520 EP - 1520 UR - https://ijcai.org/proceedings/2003/258 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
