semanticscholar8.0 / 10
Approval-directed agency and the decision theory of Newcomb-like problems
Caspar Oesterheld
Abstract
Research examining which decision theory is implemented by approval-directed agents in AI systems
Research area
agent foundationsagentic misalignmentalignment
Published
25 Feb 2019
Source
semanticscholar
Org
Center on Long-Term Risk
Sign in to read and join the discussion.