COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Churchill CompSci Talks > An introduction to Reinforcement Learning
An introduction to Reinforcement LearningAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Matthew Ireland. Reinforcement learning is inspired by the way people and most animals learn to interact with an environment. Animals are motivated by reward: they try actions and then try to remember the corresponding reward. Later, if they are in a similar situation, they can remember what action needed to be taken to achieve a reward. During my talk I will explore the basics of reinforcement learning, go into more depth of the DQN algorithm applied on Atari games and explore ways the algorithm can be improved. I will also introduce the AC3 (Asynchronous Advantage Actor-Critic) algorithm and explore successes and current research opportunities in the area. This talk is part of the Churchill CompSci Talks series. This talk is included in these lists:Note that ex-directory lists are not shown. |
Other listsMilton 400th Anniversary Lectures Centre of Latin American Studies - lectures Sustainable Development Research SeminarsOther talksMartin Roth: »Widerrede!« Finding meaning in English writing 'Nobody comes with an empty head': enterprise Hindutva and social media in urban India Drugs and Alcohol Communicating Your Research to the Wider World Emissions and Chemistry of air pollution in London and Beijing: a tale of two cities. |