✳flâneur — a map of the web's best reading
Embedded Agency (full-text version) - LessWrong
lesswrong.com · 18,504 words · saved by 1 readers
Suppose you want to build a robot to achieve some real-world goal for you—a goal that requires the robot to learn for itself and figure out a lot of…
x Embedded Agency (full-text version) — LessWrong Embedded Agency Embedded Agency Agent Foundations Mesa-Optimization Decision theory Research Agendas Goodhart's Law Robust Agents Spurious Counterfactuals Subagents Boundaries / Membranes [technical] AI Curated 228 Embedded Agency (full-text version) by Scott Garrabrant , abramdemski 15th Nov 2018 AI Alignment Forum 65 min read 17 228 Ω 55 Suppose you want to build a robot to achieve some real-world goal for you—a goal that requires the robot to learn for itself and figure out a lot of things that you don't already know. There's a complicated e
Explore this link on the map →related reading
- [1902.09469] Embedded Agencyarxiv.org
- Embedded Agency via Abstraction — AI Alignment Forumalignmentforum.org
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- The Era of Experience Paper.pdfstorage.googleapis.com
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- pdfopenreview.net
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com
- Don’t Build Multi-Agents | Cognitioncognition.ai
- The Stamp Collectormindingourway.com
- Partial Agency — LessWronglesswrong.com
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org