Natural language research announcements

[Yonatan Bisk <bisk1 AT illinois.edu>]

When:       Friday December 3 @ 2pm

Where:      3405 SC

Speaker:   Satinder Singh ( http://www.eecs.umich.edu/~baveja/ )

Title:          The Optimal Reward Problem

Abstract:   Impressive results have been obtained by research
approaches to autonomous agents that start with a given reward
function and then focus on developing theory and algorithms for
learning or planning policies that lead to high cumulative reward. In
a departure from this work, we recognize that in many situations the
starting point is an agent designer with a reward function seeking to
build an autonomous agent to act on its behalf.  What reward function
should the designer build into the autonomous agent? In this new view,
setting the parameters (agent's reward function) equal to the given
preferences (designer's reward function) implements a
preferences-parameters confound. If an agent is bounded, as most
agents are in practice, we expect that breaking the
preferences-parameters confound would be beneficial. We define the
optimal reward problem, that of designing the agent's reward function
given a designer's reward function, an agent architecture, and a
distribution over environments. The main focus of the talk will be on
a discussion of some empirical and theoretical insights obtained by
solving the optimal reward problem
** This is joint work with Jonathan Sorg and Richard Lewis at the
University of Michigan.


Bio:        Satinder Singh is a Professor of Computer Science &
Engineering at the University of Michigan and is presently also
serving as AI Lab Director. His research interests include
reinforcement learning, computational game theory and mechanism
design, and artificial intelligence.