[1902.09469] Embedded Agency
Abstract:Traditional models of rational action treat the agent as though it is cleanly separated from its environment, and can act on that environment from the outside. Such agents have a known functional relationship with their environment, can model their environment in every detail, and do not need to reason about themselves or their internal parts. We provide an informal survey of obstacles to formalizing good reasoning for agents embedded in their environment. Such agents must optimize an environment that is not of type "function"; they must rely on models that fit within the modeled environment; and they must reason about themselves as just another physical system, made of parts that can be modified and that can work at cross purposes.
# link_uwx26ffya4.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20201008011934Z - Creator=LaTeX with hyperref - ModDate=D:20201008011934Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2 - Producer=pdfTeX-1.40.21 - Trapped=False ## Contents ### Page 1 Embedded AgencyAbram Demski and Scott GarrabrantMachine Intelligence Research Institute{abram,scott}@intelligence.orgAbstractTraditional models of ra
saved by
related reading
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agencymindthefuture.info
- Embedded Agency via Abstraction — AI Alignment Forumalignmentforum.org
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
- TechnicalAgenda.pdfintelligence.org
- pdfopenreview.net
- The Stamp Collectormindingourway.com
- [2608.03958] A game theory for foundation models shows new paths to rational cooperation through similarity inferencearxiv.org
- On Functional Decision Theory :: Wolfgang Schwarzumsu.de
- Don’t Build Multi-Agents | Cognitioncognition.ai
- Approval-directed agency and the decision theory of Newcomb-like problemslink.springer.com