Waterloo.ai Seminar: Pascal Poupart on Unsupervised Video Object Segmentation for Deep Reinforcement Learning

Friday, October 4, 2019 11:00 am - 11:00 am EDT (GMT -04:00)

Please join us for the next institute seminar on Friday, October 4 at 11:00am in DC 1302.

We are excited to have our own Prof. Pascal Poupart from the department of  Computer Science to present at our AI institute seminar series! Dr. Poupart will give his perspective on the AI field and discuss some intriguing projects from his group, see more details below.

Title: Unsupervised Video Object Segmentation for Deep Reinforcement Learning

Abstract: I will present a new technique for deep reinforcement learning that automatically detects moving objects and uses the relevant information for action selection. The detection of moving objects is done in an unsupervised way by exploiting structure from motion. Instead of directly learning a policy from raw images, the agent first learns to detect and segment moving objects by exploiting flow information in video sequences. The learned representation is then used to focus the policy of the agent on the moving objects. Over time, the agent identifies which objects are critical for decision making and gradually builds a policy based on relevant moving objects. This approach, which we call Motion-Oriented REinforcement Learning (MOREL), is demonstrated on a suite of Atari games where the ability to detect moving objects reduces the amount of interaction needed with the environment to obtain a good policy. Furthermore, the resulting policy is more interpretable than policies that directly map images to actions or values with a black box neural network. We can gain insight into the policy by inspecting the segmentation and motion of each object detected by the agent. This allows practitioners to confirm whether a policy is making decisions based on sensible information. Our code is available at https://github.com/vik-goel/MOREL.

Relevant paper: Vikash Goel, Jameson Weng and Pascal Poupart, Unsupervised Video Object Segmentation for Deep Reinforcement Learning, Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018.


Prof. Pascal Poupart
Department of Computer Science  
University of Waterloo

Speaker Bio:

Pascal Poupart is a Professor in the David R. Cheriton School of Computer Science at the University of Waterloo, Waterloo (Canada) and a Canada CIFAR AI Chair at the Vector Institute. He is a principal researcher and founder of the Waterloo Borealis AI Research Lab funded by the Royal Bank of Canada. He is a faculty member of the Waterloo AI Institute. He serves as scientific advisor for Huawei Technologies and ProNavigator. 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 Natural Language Processing, Computational Finance and Telecommunication Networks. He is most well known for his contributions to the development of reinforcement learning algorithms. Notable projects that his research team are currently working on include deep learning with clear semantics, structure learning, personalized transfer learning, conversational agents, machine translation, adaptive satisfiability and sports analytics.

Pascal Poupart received a Canada CIFAR AI Chair (2018), Cheriton Faculty Fellowship (2015-2018), a best student paper honourable mention (SAT-2017), a silver medal at the SAT-2017 competition, an outstanding collaborator award from Huawei Noah's Ark (2016), a top reviewer award (ICML-2016), a gold medal at the SAT-2016 competition, a best reviewer award (NIPS-2015), an Early Researcher Award from the Ontario Ministry of Research and Innovation (2008), two Google research awards (2007-2008), a best paper award runner up (UAI-2008) and the IAPR best paper award (ICVS-2007). He serves as associate editor of the Journal of Artificial Intelligence Research (JAIR) (2017 - present), member of the editorial board of the Journal of Machine Learning Research (JMLR) (2009 - present) and guest editor for the Machine Learning Journal (MLJ) (2012 - present). He routinely serves as area chair or senior program committee member for NIPS, ICML, AISTATS, IJCAI, AAAI and UAI.

Date and Time:

Friday, October 4, 2019
11:00 AM - 12:30 PM

Location: DC 1302
Light refreshments will be available.

Seminar Recording - YouTube Link: https://www.youtube.com/watch?v=HSYf3SdvGf0