Decision-Making under Uncertainty - PowerPoint PPT Presentation

About This Presentation
Title:

Decision-Making under Uncertainty

Description:

Michael Jordan graphical models, statistics. Daphne Koller decision theory, game theory, AI ... 40 2:20 Michael Jordan Feature selection, edge ... – PowerPoint PPT presentation

Number of Views:148
Avg rating:3.0/5.0
Slides: 12
Provided by: mikej7
Category:

less

Transcript and Presenter's Notes

Title: Decision-Making under Uncertainty


1
Decision-Making under Uncertainty
http//www.cs.berkeley.edu/projects/muri
  • University of California, Berkeley
  • Venkat Anantharam
  • Laurent El Ghaoui
  • Michael I. Jordan
  • Stuart Russell
  • S. Shankar Sastry
  • University of California, Davis
  • Roger Wets
  • Stanford University
  • Daphne Koller
  • Ben van Roy
  • Claire Tomlin

2
Faculty Investigators
  • Venkat Anantharam information theory,
    stochastic control
  • Laurent El Ghaoui convex optimization, control
    theory
  • Michael Jordan graphical models, statistics
  • Daphne Koller decision theory, game theory, AI
  • Stuart Russell reinforcement learning, decision
    theory, AI
  • Shankar Sastry hybrid control, systems theory
  • Claire Tomlin hybrid control, systems theory
  • Ben van Roy reinforcement learning, dynamic
    programming
  • Roger Wets variational analysis, stochastic
    optimization

3
Postdoctoral Researchers
  • Sekhar Tatikonda information theory,
    distributed control
  • Yair Weiss probabilistic inference

4
Research Concentration Areas
  • (RCA 1) Exploration of basic methods, such as
    probability and decision theory, Bayesian and
    related methods, and utility theory
  • (RCA 2) Bound the effects of missing or incorrect
    information
  • (RCA 3) Incorporate Quality of Service issues,
    such as trading off time for certainty
  • (RCA 4) Dealing with varying bandwidth and
    connectivity in the networked battlefield
  • (RCA 5) Fusing uncertain information of different
    kinds
  • (RCA 6) Ways of structuring problems for optimal
    understanding
  • (RCA 7) Present possible and alternative courses
    of action to the user, quantitatively ranked
    according to the systems beliefs

5
Investigator to RCA Map
  • Venkat Anantharam RCA1, RCA4
  • Laurent El Ghaoui RCA1, RCA2, RCA3
  • Michael Jordan RCA1, RCA2, RCA5, RCA7
  • Daphne Koller RCA1, RCA2, RCA3, RCA5, RCA6,
    RCA7
  • Stuart Russell RCA1, RCA3, RCA5, RCA6, RCA7
  • Shankar Sastry RCA1, RCA2, RCA6
  • Claire Tomlin RCA1, RCA2, RCA6
  • Ben van Roy RCA1, RCA2, RCA3
  • Roger Wets RCA1, RCA2
  • Sekhar Tatikonda RCA1, RCA4
  • Yair Weiss RCA1, RCA2, RCA3

6
Research Spectrum
  • Physical environment
  • Information environment

Algorithms and Interfaces
Human decision maker
7
Industrial Contacts
  • Intel (Gary Bradski)
  • Google (Peter Norvig)
  • Microsoft Research (David Heckerman, Eric
    Horvitz, Jack Breese)
  • ATT Labs Research (Michael Kearns, Yann LeCun,
    Satinder Singh)
  • Affymetrix (David Kulp, Cyrus Harmon)
  • Alphatech (John Fox)
  • IBM Watson Research Center (Shivakumar
    Vaithyanathan)
  • Honeywell Labs (Datta Godbole, Mary Jo Hoffman,
    Jorge Tierno)

8
DoD/Government Contacts
  • SPAWAR, San Diego, CA
  • Third Fleet Command Ship, USS Coronado
  • Army Research Laboratories
  • SPAWAR, Norfolk, VA
  • Fort Leavenworth (TRADOC)
  • AFRL (Siva Banda)
  • AFOSR (Marc Jacobs)
  • NASA (George Meyer)
  • NASA (Asaf Degani)
  • Darpa ITO (John Bay)
  • Darpa DSO (Eric Eisenstadt)

9
Educational Activities
  • Courses specifically designed for relevance to
    MURI
  • Advanced Topics in Learning and
    Decision-Making---Berkeley
  • Statistical Learning Theory---Berkeley
  • Introduction to Convex Optimization---Berkeley
  • Optimization Seminar---Berkeley
  • Neuro-Dynamic Programming and Reinforcement
    Learning---Stanford
  • Stochastic Decision Models---Stanford
  • Analysis and Control of Nonlinear
    Systems---Stanford
  • Stochastic Programming---Davis

10
Meetings
  • Biweekly research meetings at Berkeley
  • Full-day workshop---September 20, 2000 (Berkeley)
  • Full-day workshop---March 28, 2001 (Stanford)

11
Agenda
  • 900 915 Michael Jordan (overview)
  • 915 955 Shankar Sastry Pursuit-evasion
    games, map building, embedded software
  • 955 1035 Daphne Koller Markov decision
    problems with factored value functions,
    multi-agent Markov decision problems
  • 1035 1115 Stuart Russell Programmable
    reinforcement learning systems
  • 1115 100 Lunch
  • 100 140 Claire Tomlin Distributed control
    of multiple vehicle systems
  • 140 220 Michael Jordan Feature selection,
    edge selection and variable selection
  • 220 310 Yair Weiss Approximate inference
    via approximations of free energy
  • 310 330 Break
  • 330 410 Laurent El Ghaoui Estimation and
    optimization Gaps and bridges
  • 410 430 Sekhar Tatikonda Network
    information theory
  • 430 500 Open discussion
Write a Comment
User Comments (0)
About PowerShow.com