|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 listsEED Film Series: 'Educating Rita' Dead Bodies, Living Organs: What Pathologists Really Do Department of Earth Sciences Seminars (downtown)
Other talksExploring the Universe with Gravitational Waves: LIGO and Beyond Meet the Authors Webinars for Professional Development in the Arts series 13: Psychological health of professors: Transforming university culture 2017 Lewis Lectures - week commencing 24th April Role of Adenovirus 36 in the Global Obesity Epidemic Introduction: Challenge 3. Estimating Flood Probability Using Historical Data