Current and upcoming activities
- EWRL, Steering commitee
- ALT 2012, program committee
- COLT 2012, program committee
- AISTAT 2012, reviewer
- ICML 2012, area chair
-
ALT 2011,
program co-chair with Jyrki Kivinen
- PI of a project aiming to build rotation schedules for nurses in a fully automated way
- Machine Learning Journal,
Member of Editorial Board, June 2010 -- June 2011, Action Editor, June 2011 --
- Nurturing the Statistical Machine Learning
degree specialization
program together with Edit Gombay
from the Math+Stat Department 2009--.
- Journal of Machine Learning Research,
Member of Editorial Board, June 2009--
- IEEE Transactions on Automatic Control,
Associate Editor, January 2009--
Recent activities, talks, service
- Invited
talk at
EWRL-9,
the European Workshop on Reinforcement Learning.
- Participating at the Oberwolfach workshop on
Mathematics of Machine Learning.
- Talks at COLT 2011
- Talk on learning to control linear systems with quadratic cost (LQ Problem)
with low regret
(slides)
- Talk on Agnostic KWIK learning
(slides)
-
Talk on full chararterization of the complexity
of stochastic partial monitoring
(slides)
- NIPS-2010 reviewer
- IJCAI-11, Senior program committee, member
- Monte Carlo Tree Search workshop for ICAPS'11, CFP, PC member
- Learning closed-loop policies from batch data: Model-Selection in RL,
Learning and Planning from Batch Time Series Data,
NIPS Workshop, Whistler, 2010.
- Toward the Classification of Finite Partial Monitoring Games
University of Houston, November, 2010
- How to choose cakes (if you must?) - advice from statistics
Talk presented at:
The slides are based on the talk presented in Austin.
- New algorithms for off-policy reinforcement learning and beyond
Talk presented at:
The slides are based on the talk presented at INFORMS.
- Tea-time talk on July 29, 2010: Policy iteration is strongly polynomial. Based on a recent manuscript of
Yinyu Ye.
slides, notes.
- Reinforcement Learning Algorithms for MDPs,
AAAI Tutorial, 2010 (together with Rich S. Sutton), the tutorial webpage is here.
- Reinforcement Learning and Search in Very Large Spaces, ICML 2010 Workshop,
co-organizer (with Peter Auer and
Samuel Kaski)
- UAI 2010, PC Member
- ICML 2010, Area Chair (Reinforcement learning)
- International Symposium on Mathematical Theory of Networks and Systems 2010, Reviewer
- AAAI 2010, PC Member
- AI & Statistics 2010, PC Member
- Gradient Descent Methods for Reinforcement Learning,
Washington University in St. Louis, Colloquia Series Talk, Nov 13, 2009
- Subspace method reading group, 2009 May-October
- Cryptography and beyond.
"Lunch and Learn" seminar for high school students July, 2009
- On-line Learning with Limited Feedback, COLT-09 Workshop, co-organizer.
- Active Learning in Regression over Finite Domains, University of Waterloo, AI Seminar, May 1, 2009
- Manifold-Adaptive Dimension Estimation, University of Waterloo, Statistics and Actuarial Science, April 30, 2009
- Thoughts About Planning, Barbados Workshop on Reinforcement Learning, Bellairs Institute, McGill University, Barbados, April 2009
- Recent advances in off-policy learning, Symposium on Autonomous Systems,
MPI for Biological Cybernetics, Tübingen, Germany, Jan 28--Feb 1, 2009
- IEEE, Senior Member, 2009
- ALT 2009, PC Member
- COLT 2009, PC Member
- Launching the Statistical Machine Learning degree specialization
program together with Edit Gombay
from the Math+Stat Department 2008-2009.
- The Use of Unlabeled Data in Supervised Learning: The Manifold Dossier, NIPS ´08 Workshop: New Challenges in Theoretical Machine Learning: Learning with Data-dependent Concept Spaces, Whistler, Canada, December 2008
- How Good is Forced-Exploration in Linear Stochastic Bandits?, NIPS ´08 Workshop: Model Uncertainty and Risk in Reinforcement Learning, Whistler, Canada, December 2008
- Statistical Learning Theory and Sequential Decision Making, Machine Learning Summer School, Ile de Re, France, September 2008
- Machine Learning for Health-Care Applications, ICML-08 Workshop, co-organizer.
- Active Learning in Multi-Armed Bandits, ParisTech Machine Learning Seminar, ParisTech, Ecole des Mines de Paris, Paris, May 2008
- Active Learning in Multi-Armed Bandits, Lille Machine Learning Seminar, INRIA Lille, Lille, May 2008
- Fitted/batch/model-based RL: A (sketchy, biased) overview,
Barbados Workshop on Reinforcement Learning, Bellairs Institute, McGill University, Barbados, April 2008
- Introduction to Reinforcement Learning, Machine Learning Summer School, Kioloa, March 2008
- ALT 2008, PC Member
- Sample Complexity Results for Reinforcement Learning in Large State Spaces, Towards a New Reinforcement Learning?, Whistler, NIPS Workshop, Dec 2006
- Using upper confidence bounds to control exploration and exploitation, On-line Trading of Exploration and Exploitation, Whistler, NIPS Workshop, Dec 2006
- Graduate Program Committee, Member, Dept. of Computing Science, UofA, 2008-
- Project Management Advisory Committee, Member, AICML, 2008-
- COLT 2007, PC Member
- IP & Commercialization Committee, Member, AICML, 2007-2008
- Governance & Research Committee, Member, AICML, 2007-2008
- IEEE ADPRL 2007, PC Member, special session chair
- Renewal Committee, Member, AICML, 2007
- Distinguished Lecture Series, organizer, Dept. of Computing Science, UofA, 2007
- Kernel Machines and Reinforcement Learning,
ICML-06 Workshop, co-organizer, 2006
- Communications on Artificial Intelligence, Associate Editor, 2000-
- Reviewing for the conferences ICML, AAAI, UAI, IJCAI, NIPS, CDC, ACC, ICRA and some others since many years
- Reviewing for journals like JMLR, Machine Learning, AI J., JAIR, MOR, TCS,
IEEE TNN, IEEE TAC, IEEE Spectrum, Automatica, SIAM J. COPT, Neucomp and more since many years
