AIXI ['ai̯k͡siː] is a theoretical mathematical formalism for artificial general intelligence.It combines Solomonoff induction with sequential… (More)

Semantic Scholar uses AI to extract papers important to this topic.

2016

2016

- 2016

We implemented the algorithm for learning and planning in partially observable Markov decision processes described in A Monte… (More)

Is this relevant?

2015

2015

- Benja Fallenstein, Nate Soares, Jessica Taylor
- AGI
- 2015

Solomonoff induction and AIXI model their environment as an arbitrary Turing machine, but are themselves uncomputable. This fails… (More)

Is this relevant?

2015

2015

- Jan Leike, Marcus Hutter
- UAI
- 2015

How could we solve the machine learning and the artificial intelligence problem if we had infinite computation? Solomonoff… (More)

Is this relevant?

2012

2012

- Peter Sunehag, Marcus Hutter
- AGI
- 2012

We consider extending the AIXI agent by using multiple (or even a compact class of) priors. This has the benefit of weakening the… (More)

Is this relevant?

2012

2012

- Joel Veness, Peter Sunehag, Marcus Hutter
- AGI
- 2012

One of the key challenges in AIXI approximation is model class approximation i.e. how to meaningfully approximate Solomonoff… (More)

Is this relevant?

Highly Cited

2011

Highly Cited

2011

- Joel Veness, Kee Siong Ng, Marcus Hutter, David Silver
- J. Artif. Intell. Res.
- 2011

This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. Our approach is… (More)

Is this relevant?

2011

2011

- Peter Sunehag, Marcus Hutter
- Algorithmic Probability and Friends
- 2011

We identify principles characterizing Solomonoff Induction by demands on an agent’s external behaviour. Key concepts are… (More)

Is this relevant?

2010

2010

- Joel Veness, Kee Siong Ng, Marcus Hutter, David Silver
- AAAI
- 2010

This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is… (More)

Is this relevant?

2008

2008

- Sergey Pankov
- AGI
- 2008

Universal induction solves in principle the problem of choosing a prior to achieve optimal inductive inference. The AIXI theory… (More)

Is this relevant?

2003

2003

- Marcus Hutter
- 2003

Decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability… (More)

Is this relevant?