Deep Reinforcement Learning
Abstract: Reinforcement learning is the artificial intelligence problem of machine agents that interact over time with their environments. It might only be the cherry on Yann LeCun's cake, but now combined with deep learning it's becoming increasingly prominent. Developments include control for systems including robotics and super-human achievements in games from Go to Atari to DotA 2.
Aaron will introduce deep reinforcement learning with a presentation based largely on the content of the first UC Berkeley Deep RL Bootcamp organized by Abbeel, Duan, Chen, and Karpathy. From the simplest definition of the RL problem to the latest algorithms, everyone should understand what RL is, how it might affect their work, and where it may be going.
• 6:30pm -- Networking and Refreshments
• 7:00pm -- Introduction, Announcements
• 7:15pm -- Presentation and Discussion
• 8:30pm -- Data Drinks (Tonic , 2036 G St NW)
Bio: Aaron Schumacher is a data scientist and software engineer for Deep Learning Analytics. He has taught with Python and R for General Assembly and the Metis data science bootcamp. Aaron has also worked with data at Booz Allen Hamilton, New York University, and the New York City Department of Education. He studied mathematics at the University of Wisconsin–Madison and teaching mathematics at Bard College. Aaron's career-best breakdancing result was advancing to the semi-finals of the R16 Korea 2009 individual footwork battle.