no code implementations • 19 Dec 2021 • Koen Holtman
To support this move, we define several AI cognitive architectures that combine reward maximization with other technical elements designed to improve alignment.
no code implementations • NeurIPS 2021 • Koen Holtman
The key step in counterfactual planning is to use the agent's machine learning system to construct a counterfactual world model, designed to be different from the real world the agent is in.
no code implementations • 29 Jan 2021 • Koen Holtman
The key step in counterfactual planning is to use an AGI machine learning system to construct a counterfactual world model, designed to be different from the real world the system is in.
no code implementations • 10 Jul 2020 • Koen Holtman
We present an AGI safety layer that creates a special dedicated input terminal to support the iterative improvement of an AGI agent's utility function.
1 code implementation • 5 Aug 2019 • Koen Holtman
The results in this paper were obtained by concurrently developing an AGI agent simulator, an agent model, and proofs.