International Conference on Algorithmic DecisionTheory

ADT 2015: Algorithmic Decision Theory pp 205-221

Sequential Extensions of Causal and Evidential Decision Theory

Conference paper

DOI: 10.1007/978-3-319-23114-3_13

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9346)
Cite this paper as:
Everitt T., Leike J., Hutter M. (2015) Sequential Extensions of Causal and Evidential Decision Theory. In: Walsh T. (eds) Algorithmic Decision Theory. ADT 2015. Lecture Notes in Computer Science, vol 9346. Springer, Cham

Abstract

Moving beyond the dualistic view in AI where agent and environment are separated incurs new challenges for decision making, as calculation of expected utility is no longer straightforward. The non-dualistic decision theory literature is split between causal decision theory and evidential decision theory. We extend these decision algorithms to the sequential setting where the agent alternates between taking actions and observing their consequences. We find that evidential decision theory has two natural extensions while causal decision theory only has one.

Keywords

Evidential decision theory Causal decision theory Planning Causal graphical models Dualism Physicalism 

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Australian National UniversityCanberraAustralia

Personalised recommendations