Charles Gretton
About Me:
I have recently joined the Intelligent Robotics Lab at the University of Birmingham. I also hold an adjunct position with Griffith University IIIS. In the recent past I was a researcher with Abdul Sattar's
"SAFE Agents work package" within NICTA (National Information and
Computer Technology Australia). Before that I was a PhD student at the Computer Sciences Laboratory at the Australian National University.
My primary interests
Artificial intelligence:
Planning -- decision-theoretic planning, planning with non-Markovian
rewards and dynamics, control knowledge, relational generalisation in
planning
Machine Learning -- unsupervised and supervised relational
reinforcement learning, policy gradient, explanation based
(analytical) learning
Knowledge Representation and Reasoning -- reasoning about actions,
semantic web (ontology) and description logic
Search -- stochastic local search, anytime algorithms
Contact:
Address:
PO Box 6020,
St Lucia QLD 4067
| E-mail: |
charles.gretton@nicta.com.au
|
| Telephone: |
(+61) (07) 3300 8581
|
| Fax: |
(+61) (07) 3000 8420
|
Papers
Planning:
- N. Robinson, C. Gretton, D. Pham, and
A. Sattar. A Compact and Efficient SAT Encoding for
Planning. International Conference on Automated
Planning and Scheduling (ICAPS-08). 2008.
[
pdf] ©
AI Acces Foundation
- C. Gretton. Gradient-Based Relational Reinforcement-Learning
of Temporally Extended Policies. International Conference on Automated
Planning and Scheduling (ICAPS-07). 2007.
[
pdf] ©
AI Acces Foundation
- S.
Thiébaux, C. Gretton, J. Slaney, D. Price, and F.
Kabanza. Decision-Theoretic Planning with non-Markovian Rewards.
Journal of Artificial Intelligence Research 25:17-74, January 2006.
[
pdf] ©
AI Acces Foundation
- C. Gretton and S. Thiébaux. Exploiting First-Order
Regression in Inductive Policy Selection. 20th Conference on
Uncertainty in Artificial Intelligence (UAI-04) Morgan Kaufmann, Banf
(Canada), July 2004. © the authors.
[
ps.gz,
pdf]
- Extended Abstract:
ICML-04. Appearing in Proceedings of
the ICML'04 workshop on Relational Reinforcement Learning,
Banff, Canada, 2004. © the authors.
- C. Gretton, D. Price and S. Thiébaux. Implementation and
Comparison of Solution Methods for Decision Processes with
Non-Markovian Rewards. 19th Conference on Uncertainty in
Artificial Intelligence (UAI-03), Morgan Kaufmann, Acapulco (Mexico),
August 2003. © the authors.
[
ps.gz,
pdf]
- Extended Version:
ICAPS-03
Workshop on Planning under Uncertainty and Incomplete Information, Trento (Italy), June 2003. © the authors.
Stochastic Local Search:
- D. Pham, J. Thornton, C. Gretton, and A.
Sattar. Combining Adaptive and Dynamic Local Search for
Satisfiability. Journal on Satisfiability, Boolean Model Checking, and
Computation, 2008.
- S.Richter, M.Helmert and C.Gretton. A Stochastic Local Search
Approach to Vertex Cover. Proceedings of the 30th German Conference on
Artificial Intelligence (KI-2007), 2007.
-
D-N.Pham, J.Thornton, C.Gretton, and A.Sattar.
Advances in Local Search for Satisfiability.
Proceedings of the 20th Australian Joint Conference
on Artificial Intelligence, 2007.
Proceedings: Lecture Notes in Computer Science, 4830, pp. 213-222, Heidelberg: Springer.
Biological Taxonomy:
- K. Taylor, C. Gretton. Ants caught in the Semantic Web: A study
in the application of description logic to animal systematics. 16th
International Conference on Scientific and Statistical Database
Management, IEEE, Santorini Island Greece, 21-23 June 2004.
Robotics:
- F. Werner, C.
Gretton, F. Maire, and J. Sitte. Induction of Topological Environment
Maps from Sequences of Visited Places. IEEE/RSJ 2008
International Conference on Intelligent RObots and Systems, 2008.
Students
Silvia Richter :: webpage
Nathan Robinson :: Probabilistic planning using SSAT problem representations.
Software
- CO-PLAN (2008) -- co-author with Nathan Robinson and Duc-Nghia Pham. Combining SAT-Based Planning with Forward-Search
- ayPlan
(2008) -- Cost-optimal (also has a satisficing mode) state-based
propositional planning (this is a module from CO-Plan)
- Evacuator (2007) -- co-author with Duc-Nghia Pham. Simulates pedestrian evacuation from the Brisbane CBD (email me for details)
- gNovely+ -- second author with Duc-Nghia Pham. 1st place in the random category of the 2007 SAT competition
- RRL (2004 / 2005) -- see my ICAPS-07 paper
- NMRDPP
(2003) -- Non-Markovian
Reward Decision Process Planner. 2nd place in the open and control
knowledge tracks of the 2004 International Probabilistic Planning
Competition
Teaching
(2006; co-lecturer with Duc-Nghia Pham) "Griffith -- 6206INT -- Advanced Topics in Info Tech B"
(2003; tutor) "ANU -- comp2310 -- Concurrent and Distributed Systems"
Appy polly loggy if this is all chepooka:
Some interesting music (7/1998, 9/1998)
1939 -- 7,277 :: <<It was a period when a literary panning, published in a review, could give you something to
think about for thirty years.>>
-- from :: "Sartre: The Philosopher of the Twentieth Century'', Bernhard-Henri Lévy.

** Departing Monday 7 Jul 2305, and
arriving Tuesday 8 July :: Lufthansa LH779 Singapore to Frankfurt row
52 seat J. It was raining in Wellington during takeoff.