Probabilistic evaluation of sequential plans from causal models with hidden variables

Authors:
Judea Pearl;James Robins
Affiliations:
Cognitive Systems Laboratory, Computer Science Department, University of California, Los Angeles, Los Angeles, CA;Departments of Epidemiology & Biostatistics, School of Public Health, Harvard University, Boston, MA
Venue:
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Year:
1995

Citing 0
Cited 13

Data mining tasks and methods: Probabilistic and casual networks: methodology for probabilistic networks

Handbook of data mining and knowledge discovery
Identifying conditional causal effects

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Complete Identification Methods for the Causal Hierarchy

The Journal of Machine Learning Research
IDENTIFIABILITY IN CAUSAL BAYESIAN NETWORKS: A GENTLE INTRODUCTION

Cybernetics and Systems
Identifying linear causal effects

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Identifiability in causal Bayesian networks: a sound and complete algorithm

AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Identification of joint interventional distributions in recursive semi-Markovian causal models

AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
On the completeness of an identifiability algorithm for semi-Markovian models

Annals of Mathematics and Artificial Intelligence
Testing edges by truncations

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Causal analysis with Chain Event Graphs

Artificial Intelligence
On the testability of causal models with latent and instrumental variables

UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Estimation of effects of sequential treatments by reparameterizing directed acyclic graphs

UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Causal identifiability via Chain Event Graphs

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper concerns the probabilistic evaluation of plans in the presence of unmeasured variables, each plan consisting of several concurrent or sequential actions. We establish a graphical criterion for recognizing when the effects of a given plan can be predicted from passive observations on measured variables only. When the criterion is satisfied, a closed-form expression is provided for the probability that the plan will achieve a specified goal.