#### Filter Results:

#### Publication Year

2013

2017

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

- Matteo Brunelli, Andrew Critch, Michele Fedrizzi
- Applied Mathematics and Computation
- 2013

A note on the proportionality between some consistency indices in the AHP Abstract Analyzing the consistency of preferences is an important step in decision making with pairwise comparison matrices, and several indices have been proposed in order to estimate it. In this paper we prove the proportionality between some consistency indices in the framework of… (More)

We quantify the representational power of matrix product states (MPS) for entangled qubit systems by giving polynomial expressions in a pure quantum state's amplitudes which hold if and only if the state is a translation invariant matrix product state or a limit of such states. For systems with few qubits, we give these equations explicitly, considering… (More)

- Andrew Critch
- ArXiv
- 2016

Löb's theorem and Gödel's theorems make predictions about the behavior of systems capable of self-reference with unbounded computational resources with which to write and evaluate proofs. However, in the real world, systems capable of self-reference will have limited memory and processing speed, so in this paper we introduce an effective version of Löb's… (More)

We survey eight research areas organized around one question: As learning systems become increasingly intelligent and autonomous, what design principles can best ensure that their behavior is aligned with the interests of the operators? We focus on two major technical obstacles to AI alignment: the challenge of specifying the right kind of objective… (More)

- Scott Garrabrant, Tsvi Benson-Tilsen, Andrew Critch, Nate Soares, Jessica Taylor
- Electronic Colloquium on Computational Complexity
- 2016

We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time. For instance, if the language is Peano arithmetic, it assigns probabilities to all arithmetical statements, including claims about the twin prime conjecture, the outputs of long-running computations,… (More)

- Andrew Critch
- ArXiv
- 2017

Existing multi-objective reinforcement learning (MORL) algorithms do not account for objectives that arise from players with differing beliefs. Concretely, consider two players with different beliefs and utility functions who may cooperate to build a machine that takes actions on their behalf. A representation is needed for how much the machine's policy… (More)

We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time. For instance, if the language is Peano arithmetic, it assigns probabilities to all arithmetical statements, including claims about the twin prime conjecture, the outputs of long-running computations,… (More)

- ‹
- 1
- ›