The big world hypothesis
- 2025-09-28
“In many decision-making problems the agent is orders of magnitude smaller than the environment.”
Definition:1
The big world hypothesis says that in many decision-making problems the agent is orders of magnitude smaller than the environment. It can neither fully perceive the state of the world nor can it represent the value or optimal action for every state. Instead, it must learn to make sound decisions using its limited understanding of the environment. The key research challenge for achieving goals in big worlds is to come up with solution methods that efficiently utilize the limited resources of the agent.
Opposing view:
The opposing view to the big world hypothesis is that real-world decision-making problems have a simple solution. The agent is not only capable of representing the simple solution but also has additional capacity that can be used to search for the solution more efficiently—they are overparameterized. The key research challenge for achieving goals with over-parameterized agents is to find the solution that enables optimal decision-making in perpetuity.
메모
The big world hypothesis는 허버트 사이먼의 제한된 합리성 개념을 AI 맥락에서 다시 표현한 것으로 보인다. —AK, 2025-09-28