Using learned PSR model for planning under uncertainty

Authors:
Yunlong Liu;Guoli Ji;Zijiang Yang
Affiliations:
Department of Automation, Xiamen University, Xiamen, China;Department of Automation, Xiamen University, Xiamen, China;School of Information Technology, York University, Toronto, Canada
Venue:
AI'10 Proceedings of the 23rd Canadian conference on Advances in Artificial Intelligence
Year:
2010

Citing 5
Cited 1

Multivariate statistical methods: a primer

Multivariate statistical methods: a primer
Learning and discovery of predictive state representations in dynamical systems with reset

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Predictive state representations: a new theory for modeling dynamical systems

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
A planning algorithm for predictive state representations

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Discovery and learning of models with predictive state representations for dynamical systems without reset

Knowledge-Based Systems

Learning dialogue POMDP models from data

Canadian AI'11 Proceedings of the 24th Canadian conference on Advances in artificial intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

As an alternative to partially observable Markov decision processes (POMDPs), Predictive State Representations (PSRs) is a recently developed method to model controlled dynamical systems While POMDPs and PSRs provide general frameworks for solving the problem of planning under uncertainty, they rely crucially on having a known and accurate model of the environment However, in real-world applications it can be extremely difficult to build an accurate model In this paper, we use learned PSR model for planning under uncertainty, where the PSR model is learned from samples and may be inaccurate We demonstrate the effectiveness of our algorithm on a standard set of POMDP test problems Empirical results show that the algorithm we proposed is effective.