Asymptotically Optimal Agents


METADATA ONLY
Loading...

Date

2011

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.

Permanent link

Publication status

published

Book title

Algorithmic Learning Theory

Volume

6925

Pages / Article No.

368 - 382

Publisher

Springer

Event

22nd International Conference on Algorithmic Learning Theory (ALT 2011)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Rational agents; Sequential decision theory; Artificial general intelligence; Reinforcement learning; Asymptotic optimality; General discounting

Organisational unit

03659 - Buhmann, Joachim M. (emeritus) / Buhmann, Joachim M. (emeritus) check_circle

Notes

Funding

Related publications and datasets