- June 13th, 2011: Release
of my GapMin code for flat POMDPs with
improved bounds on the optimal value.
- Sept 1st, 2010: I am
co-organizing (with Jesse Hoey and Thomas Ploetz) the NIPS-10 workshop on Machine
for Assistive Technologies on Dec 10, 2010 in Whistler,
- May 3rd, 2010: Kee Eung
Kim and I will give
a tutorial on Partially
Observable Markov Decision Processes at PRICAI on August 30th, 2010 in
Daegu, South Korea.
- February 5th 2010: I'm
co-organizing (with Matthijs Spaan, Joelle Pineau, Jason Williams and
Guy Shani) the POMDP
Practitioners Workshop: Solving Real-World POMDP Problems at ICAPS 2010 on May 12-13 in
Toronto, ON, Canada.
- November 1st 2009: I'm
co-organizing (with Marcus Hutter, Willliam Uther and Kee Siong Ng) the
NIPS-09 mini symposium on Partially Observable
Reinforcement Learning on Dec 10, 2009 in Vancouver, BC, Canada.
- March 26, 2009: I gave an
invited talk at Google on Non-Myopic
Learning: A Reinforcement Learning Approach, which is
available on youtube.
- Sept 15, 2008: I am
co-organizing (with Mohammad Ghavamzadeh, Yaakov Engel and Shie Mannor)
the NIPS-08 workshop on
Model Uncertainty and Risk in
Reinforcement Learning on Dec 13, 2008 in Whistler, BC, Canada.
- Aug 12, 2008: The UAI-08 best paper award runner up was given
to the paper Hierarchical
POMDP Optimization by Maximum Likelihood Maximization co-authored
by Marc Toussaint, Laurent Charlin and Pascal Poupart.
- July 21, 2008: I received
an Early Researcher Award from
the Ontario Ministry of Research & Innovation (competitive honour
for top Ontario researchers).
- May 5, 2008: I am
co-organizing (with Guy Shani, Trey Smith and Joelle Pineau) the
workshop on Advancements
POMDP Solvers at AAAI-08 on July 14 in Chicago, Illinois.
- Apr 17, 2007: Release of
my symbolic Perseus code for large
- Apr 6, 2007: I will give
a tutorial on Bayesian
methods for reinforcement learning at ICML on June 20th, 2007 (with
and Yaakov Engel).
- Mar 24, 2007: The IAPR best paper award at ICVS-07 was
given to the paper Assisting
Persons with Dementia during Handwashing using a Partially Observable
Markov Decision Process co-authored by Jesse Hoey, Axel von
Bertoldi, Pascal Poupart and Alex Mihailidis.