Sequential Extensions of Causal and Evidential Decision Theory

2015/06/24 by Tom Everitt, Jan Leike, Everitt, Tom +3 · 2 citations
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Auction Theory and Applications #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge

paper · pdf · doi:10.48550/arxiv.1506.07359

openalex publication_date 2015/06/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Causal decision theory
• Some Counterexamples to Causal Decision Theory

Cited by

• AI Safety Gridworlds
• Avoiding Wireheading with Value Reinforcement Learning

Related

• Some Counterexamples to Causal Decision Theory
• Characterising Decision Theories with Mechanised Causal Graphs
• Symptomatic Acts and the Value of Evidence in Causal Decision Theory
• Cheating Death in Damascus
• Playing against Nature: causal discovery for decision making under uncertainty