Science, Technology & the Future | Marcus Hutter - Advances in Universal Artificial Intelligence - AGI17 @scfu | Uploaded December 2018 | Updated October 2024, 9 hours ago.
Abstract: There is great interest in understanding and constructing generally
intelligent systems approaching and ultimately exceeding human
intelligence. Universal AI is such a mathematical theory of machine super-intelligence. More precisely, AIXI is an elegant parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment that possesses essentially all aspects of rational intelligence. The theory reduces all conceptual AI problems to pure computational questions. After a brief discussion of its philosophical, mathematical, and computational ingredients, I will give a formal definition and measure of intelligence, which is maximized by AIXI. AIXI can be viewed as the most powerful Bayes-optimal sequential
decision maker, for which I will present general optimality results. This also motivates some variations such as knowledge-seeking and optimistic agents, and feature reinforcement learning. Finally I present some recent approximations, implementations, and applications of this modern top-down approach to AI.
Paper: hutter1.net/publ/suaiheavy.pdf
Many thanks for watching!
Consider supporting SciFuture by:
a) Subscribing to the SciFuture YouTube channel: youtube.com/subscription_center?add_user=TheRationalFuture
b) Donating
- Bitcoin: 1BxusYmpynJsH4i8681aBuw9ZTxbKoUi22
- Ethereum: 0xd46a6e88c4fe179d04464caf42626d0c9cab1c6b
- Patreon: patreon.com/scifuture
c) Sharing the media SciFuture creates: scifuture.org
Kind regards,
Adam Ford
- Science, Technology & the Future
Abstract: There is great interest in understanding and constructing generally
intelligent systems approaching and ultimately exceeding human
intelligence. Universal AI is such a mathematical theory of machine super-intelligence. More precisely, AIXI is an elegant parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment that possesses essentially all aspects of rational intelligence. The theory reduces all conceptual AI problems to pure computational questions. After a brief discussion of its philosophical, mathematical, and computational ingredients, I will give a formal definition and measure of intelligence, which is maximized by AIXI. AIXI can be viewed as the most powerful Bayes-optimal sequential
decision maker, for which I will present general optimality results. This also motivates some variations such as knowledge-seeking and optimistic agents, and feature reinforcement learning. Finally I present some recent approximations, implementations, and applications of this modern top-down approach to AI.
Paper: hutter1.net/publ/suaiheavy.pdf
Many thanks for watching!
Consider supporting SciFuture by:
a) Subscribing to the SciFuture YouTube channel: youtube.com/subscription_center?add_user=TheRationalFuture
b) Donating
- Bitcoin: 1BxusYmpynJsH4i8681aBuw9ZTxbKoUi22
- Ethereum: 0xd46a6e88c4fe179d04464caf42626d0c9cab1c6b
- Patreon: patreon.com/scifuture
c) Sharing the media SciFuture creates: scifuture.org
Kind regards,
Adam Ford
- Science, Technology & the Future