Hierarchical Planning as Inference
Pascal Poupart (University of Waterloo)
NICTA SML SEMINARDATE: 2011-02-17
TIME: 11:00:00 - 12:00:00
LOCATION: NICTA - 7 London Circuit
CONTACT: JavaScript must be enabled to display this email address.
ABSTRACT:
Planning as inference recently emerged as a new paradigm that allows practitioners to leverage inference techniques in planning. More precisely, MDPs and POMDPs can be transformed into maximum a posteriori hypothesis problems that can be tackled by expectation maximization. This framework is quite general in the sense that hierarchical, hybrid and multi-agent planning problems can be tackled with the same machinery. In this talk, I will focus on hierarchical planning. I will explain how hierarchy discovery and planning can be done simultaneously.
Relevant paper:
Automated Hierarchy Discovery for Planning in Partially Observable Environments Laurent Charlin, Pascal Poupart and Romy Shioda In Advances in Neural Information Processing Systems 19 (NIPS), Vancouver, BC, 2006. http://www.cs.uwaterloo.ca/~ppoupart/publications/hierarchy/hierarchyDiscovery_NIPS07.pdf
BIO:
Pascal Poupart is an Associate Professor in the David R. Cheriton School of Computer Science at the University of Waterloo, Waterloo (Canada). He received the B.Sc. in Mathematics and Computer Science at McGill University, Montreal (Canada) in 1998, the M.Sc. in Computer Science at the University of British Columbia, Vancouver (Canada) in 2000 and the Ph.D. in Computer Science at the University of Toronto, Toronto (Canada) in 2005. His research focuses on the development of algorithms for reasoning under uncertainty and machine learning with application to Assistive Technologies, Natural Language Processing and Information Retrieval. He is most well known for his contributions to the development of approximate scalable algorithms for partially observable Markov decision processes (POMDPs) and their applications in real-world problems, including automated prompting for people with dementia for the task of handwashing and spoken dialog management. Other notable projects that his research team are currently working on include a smart walker to assist older people and a wearable sensor system to assess and monitor the symptoms of Alzheimer's disease.
Pascal Poupart received the Early Researcher Award, a competitive honor for top Ontario researchers, awarded by the Ontario Ministry of Research and Innovation in 2008. He was also a co-recipient of the Best Paper Award Runner Up at the 2008 Conference on Uncertainty in Artificial Intelligence (UAI) and the IAPR Best Paper Award at the 2007 International Conference on Computer Vision Systems (ICVS). He is a member of the editorial board of the Journal of Artificial Intelligence Research (JAIR) and the Journal of Machine Learning Research (JMLR). His research partners include Google, Intel, the Alzheimer's Association, the UW-Schlegel Research Institute for Aging, Sunnybrook Health Science Centre and the Toronto Rehabilitation Institute.
