Workshop: Engineering and Reverse Engineering Reinforcement Learning

Engineering and Reverse Engineering Reinforcement Learning
July 18, 2014 - 10:00 am to 1:30 pm

Summary: Psychologists and neuroscientists routinely borrow ideas from machine learning to understand and model reinforcement learning in humans and animals. Likewise, ideas from psychology and neuroscience filter into machine learning in a variety of ways. The goal of the workshop is to highlight some of the theoretical synergies that have arisen from this cross-pollination. The symposium will cover three topics (see below), each addressed by one cognitive scientist/neuroscientist and one computer scientist.


10am-10:05am: Introduction and welcome

Session 1: Learning to learn
10:05-10:30: Michael Littman (Brown)
10:30-10:55: Michael Frank (Brown)
10:55-11:10: discussion

Session 2: Inverse reinforcement learning and theory of mind
11:10-11:35: Monica Babes-Vroman (Rutgers)
11:35-12:00: Chris Baker (MIT)
12:00-12:15: discussion

12:15-1:00: lunch

Session 3: Intrinsic motivation and exploration
1:00-1:25: Laura Schulz (MIT)
1:25-1:50: Andrew Barto (UMass Amherst)
1:50-2:05: discussion

Workshop is co-organized by the MIT Intelligence Initiative (MIT I^2) and the Center for Brains, Minds and Machines (CBMM.)

This workshop if free and open to the public. Registration required.


July 18, 2014
10:00 am to 1:30 pm
MIT: McGovern Institute Singleton Auditorium, 46-3002

43 Vassar Street, MIT Bldg 46, Cambridge, 02139 United States