Sciweavers

Share
ALDT
2015
Springer

Sequential Extensions of Causal and Evidential Decision Theory

4 years 10 months ago
Sequential Extensions of Causal and Evidential Decision Theory
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, causal graphical models, planning, dualism, physicalism.
Tom Everitt, Jan Leike, Marcus Hutter
Added 15 Apr 2016
Updated 15 Apr 2016
Type Journal
Year 2015
Where ALDT
Authors Tom Everitt, Jan Leike, Marcus Hutter
Comments (0)
books