|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Universal Bayesian Agents: Theory and Applications
If you have a question about this talk, please contact Zoubin Ghahramani.
The dream of creating artificial devices that reach or outperform human intelligence is many centuries old. In this talk I present 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. The necessary and sufficient ingredients are Bayesian probability theory; algorithmic information theory; universal Turing machines; the agent framework; sequential decision theory; and reinforcement learning, which are all important subjects in their own right. I also present some recent approximations, implementations, and applications of this modern top-down approach to AI.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsSustainable Resources Research Group Cambridge Judge Business School Ecology Lunchtime Series
Other talksPostgraduate Diploma in Entrepreneurship webinar The Future of the UN Discerning the food from the trees Gender, sexuality and illness in early modern exorcism De-identified electronic mental health records for research and recruitment 150 years of regional GDP: United Kingdom and Ireland