420 Maynard St.
Ann Arbor, MI 48109-1327
www.michigandaily.com
NISA KHAN
Editor in Chief
734-418-4115 ext. 1251
nisakhan@michigandaily.com
JUEUI HONG
Business Manager
734-418-4115 ext. 1241
jueuih@michigandaily.com
EDITORIAL STAFF
Dayton Hare
Managing Editor
haredayt@michigandaily.com
Jennifer Meer Managing News Editor
news@michigandaily.com
SENIOR NEWS EDITORS: Andrew
Hiyama, Kaela Theut
Sarah Khan Editorial Page Editor
tothedaily@michigandaily.com
Jacob Shames Managing Sports Editor
sportseditors@michigandaily.com
Will Stewart Managing Arts Editor
arts@michigandaily.com
SENIOR ARTS EDITOR: Dom Polsinelli
Alexis Rankin
and Max Kuang Managing Photo Editors
photo@michigandaily.com
Michelle Phillips Managing Design Editor
design@michigandaily.com
Emily Miiller Managing Copy Editor
copydesk@michigandaily.com
SENIOR COPY EDITOR: Ashley Woonton
Christian Paneda Managing MiC Editor
michiganincolor@michigandaily.com
Abe Lofy Managing Video Editor
video@michigandaily.com
Ishan Vashinta Managing Web Editor
ivashi@michigandaily.com
Ellie Homant Managing Social Media Editor
CONTACT INFORMATION
Newsroom Office hours:
Sun.-Thurs. 11 a.m. - 2 a.m.
734-763-2459 opt.3
News Tips news@michigandaily.com
Corrections
corrections@michigandaily.com
Letters to the Editor tothedaily@michigandaily.com
or visit michigandaily.com/letters
Photo Department photo@michigandaily.com
Arts Section arts@michigandaily.com
Editorial Page opinion@michigandaily.com
Sports Section sports@michigandaily.com
Magazine statement@michigandaily.com
Advertising Phone: 734-418-4115
Department dailydisplay@gmail.com
The Michigan Daily (ISSN 0745-967) is
published every Thursday during the
spring and summer terms by students
at the University of Michigan. One copy
is available free of charge to all readers.
Additional copies may be picked up at the
Daily’s office for $2. Subscriptions for fall
term, starting in September, via U.S. mail
are $110. Winter term (January through
April) is $115, yearlong (September
through April) is $195. University affiliates
are subject to a reduced subscription rate.
On-campus subscriptions for fall term
are $35. Subscriptions must be prepaid.
The Michigan Daily is a member of The
Associated Press and The Associated
Collegiate Press.
2
Thursday, June 15, 2017
The Michigan Daily — michigandaily.com
NEWS
Rackham conference showcases findings
and innovations in decision-making
The four-day event
brought together
researchers, students
and professionals
across disciplines
By JENNIFER MEER
Summer Managing News Editor
The
third
Multidisciplinary
Conference
on
Reinforcement
Learning and Decision Making
took place at the Rackham Graduate
School
between
Sunday
and
Thursday this week.
Reinforcement learning refers to
the relationship between the agent
— like a person or robot, for example
— and the environment — like a
video game or puzzle the agent is
trying to complete. The environment
represents a certain state of being,
while the agent acts upon that state
and receives a reward, or response.
The
four-day
event
saw
researchers,
professionals
and
students from several disciplines,
including psychology and computer
science, come together to discuss
discoveries
and
innovations
in
decision-making.
Among
the
event
speakers
were Ece Kamar, a researcher
from Microsoft who specializes in
artificial intelligence, Joelle Pineau,
an assistant professor of computer
science at McGill University and Kent
Berridge, James Olds Distinguished
University Professor of Psychology
and Neuroscience at the University of
Michigan.
The days were broken into sessions
of several brief presentations from
speakers describing their work.
On
Tuesday
afternoon,
Max
Kleiman-Weiner, a Ph.D. student in
Computational Cognitive Science
at MIT, presented “Learning to
Cooperate and Compete.”
Prefacing his address with a
quote from psychologist Nicholas
Humphrey, Kleiman-Weiner related
social interactions to games —
incorporating elements of game
theory in his presentation.
From a research standpoint, games
like tic-tac-toe and checkers have
effectively been solved and can be
modeled by computers, he explained.
There are other games where
computers can act like humans, but
cannot necessarily solve the game,
such as in a game of chance.
“It’s these kinds of ad hoc
interactions
that
involve
lots
of
complexity,
where
you’re
cooperatively playing a game, but
there might be aspects of competition
in that game that can explain a lot of
the richness of human cooperative
behavior in a lot of that real world
contexts that we might want to have
machines working with us and at
least understanding us, so things
like how to negotiate, playground
games,” he said. “We want to study
cooperation.”
There are models for studying
cooperation,
one
of
which
is
the prisoner’s dilemma, which
highlights
a
struggle
between
what is good for the well-being of
both players versus what is more
advantageous to a single player.
Mathematically, the dilemma points
to tension between cooperation and
competition but, experimentally, it
doesn’t capture several important
factors, according to Kleiman-
Weiner.
He
explained
his
team
of
researchers designed a system to
overcome obstacles presented in
current models of cooperation.
“What we’ve done… to study
these questions both in a way where
we can build more models and look
at human behavior is to take an
approach that’s been well studied
in multi-agent systems literature,”
he said.
The
team
developed
games
with
naturalistic
environments
that people can play intuitively,
like video games. The games can
represent different social situations.
“If we have these programs, we
can sort of reconstruct the original
social dilemma and think, ‘Well,
I have this choice to cooperate or
compete, and that corresponds
to certain rewards,’ ” he said. “In
reality, it’s a lot more challenging
than that.”
Different ways of implementing
potential plans yield different
payoffs,
Kleiman-Weiner
explained. However, the team aims
to build algorithms to play the
games.
Difficulties
arise
when
the
researchers want to be able to
plan at a high level of abstraction
—
determining
cooperation
or competition — but need to
implement these goals through
low-level actions, like moves in
a game. They need to be able to
determine if certain low-level
actions confirm the higher-level
goals. Furthermore, they also
want to coordinate cooperation
across different scenarios, so as
to generalize and create coherent
plans to tackle certain games.
Overall,
the
researchers
aim to make plans for using
generalizations and best-response
scenarios for competition and
coordination using reinforcement
learning.
COURTESY OF JENNIFER MEER
MIT graduate student Max Kleiman-Weiner presents at the third annual
Multidiscipliary Conference on Reinforcement Learning and Decision Making at
Rackham Graduate School.
Read more at MichiganDaily.com