Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning.

François Rivest

Nilaksh Antoine Clavaud Mathieu Reymond François Rivest Sarath Chandar Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning. 2026 February abs/2602.09396 CoRR https://doi.org/10.48550/arXiv.2602.09396 db/journals/corr/corr2602.html#abs-2602-09396 streams/journals/corr

Behnoush Khavari Mehran Shakerinava Jayesh Khullar Jerry Huang François Rivest Siamak Ravanbakhsh Sarath Chandar Parity Requires Unified Input Dependence and Negative Eigenvalues in SSMs. 2025 August abs/2508.07395 CoRR https://doi.org/10.48550/arXiv.2508.07395 db/journals/corr/corr2508.html#abs-2508-07395 streams/journals/corr

Konur Tholl François Rivest Mariam El Mezouar Ranwa Al Mallah Large Language Model Integration with Reinforcement Learning to Augment Decision-Making in Autonomous Cyber Operations. 2025 September abs/2509.05311 CoRR https://doi.org/10.48550/arXiv.2509.05311 db/journals/corr/corr2509.html#abs-2509-05311 streams/journals/corr

Ruikang Luo Aman Anand Farhana H. Zulkernine François Rivest YOLO-I3D: Optimizing Inflated 3D Models for Real-Time Human Activity Recognition. 269 2024 10 J. Imaging 11 https://doi.org/10.3390/jimaging10110269 db/journals/jimaging/jimaging10.html#LuoAZR24 streams/journals/jimaging

Justin Norman François Rivest Monte Carlo Tree Search Satellite Scheduling Under Cloud Cover Uncertainty. 2024 abs/2405.20951 CoRR https://doi.org/10.48550/arXiv.2405.20951 db/journals/corr/corr2405.html#abs-2405-20951

Shashi Suman François Rivest Ali Etemad Toward Personalization of User Preferences in Partially Observable Smart Home Environments. 549-561 2023 June 4 IEEE Trans. Artif. Intell. 3 https://doi.org/10.1109/TAI.2022.3178065 db/journals/tai/tai4.html#SumanRE23

Mohammed Gasmallah François Rivest Farhana H. Zulkernine Mélanie Breton Quantifying Path Smoothness in Video Object Tracking by Detection. 2023 Canadian AI https://doi.org/10.21428/594757db.f0bc10fd conf/ai/2023 db/conf/ai/ai2023.html#GasmallahRZB23 Ruikang Luo François Rivest Farhana H. Zulkernine I3D Light - A Simple Motion Information Stream for I3D. 2023 Canadian AI https://doi.org/10.21428/594757db.dffcb184 conf/ai/2023 db/conf/ai/ai2023.html#LuoRZ23 Masih Hashemi François Rivest Optimistically Initializing DQN. 179-184 2023 CASCON https://dl.acm.org/doi/10.5555/3615924.3615945 conf/cascon/2023 db/conf/cascon/cascon2023.html#HashemiR23

Abdellah Chehri Gwanggil Jeon François Rivest Hussein T. Mouftah Evolution and Trends in Artificial Intelligence of Things Security: When Good Enough is Not Good Enough! 62-66 2022 5 IEEE Internet Things Mag. 3 https://doi.org/10.1109/IOTM.001.2100130 db/journals/iotm/iotm5.html#ChehriJRM22

Shashi Suman Ali Etemad François Rivest Potential Impacts of Smart Homes on Human Behavior: A Reinforcement Learning Approach. 567-580 2022 3 IEEE Trans. Artif. Intell. 4 https://doi.org/10.1109/TAI.2021.3127483 db/journals/tai/tai3.html#SumanER22

Richard Kohar François Rivest Alain Gosselin ChronosPerseus: Randomized Point-based Value Iteration with Importance Sampling for POSMDPs. 2022 abs/2207.07825 CoRR https://doi.org/10.48550/arXiv.2207.07825 db/journals/corr/corr2207.html#abs-2207-07825

Alex Salgo Jeremy Banks François Rivest Exploring decision support systems in task scheduling. 184-189 2021 CASCON https://dl.acm.org/doi/10.5555/3507788.3507814 conf/cascon/2021 db/conf/cascon/cascon2021.html#SalgoBR21 Isaac Hogan Donghao Qiao Ruikang Luo Mojtaba Moattari Austin Carthy Farhana H. Zulkernine François Rivest Mélanie Breton FireWarn: Fire Hazards Detection Using Deep Learning Models. 1-10 2021 CogMI https://doi.org/10.1109/CogMI52975.2021.00010 conf/cogmi/2021 db/conf/cogmi/cogmi2021.html#HoganQLMCZRB21

Shashi Suman Ali Etemad François Rivest Potential Impacts of Smart Homes on Human Behavior: A Reinforcement Learning Approach. 2021 abs/2102.13307 CoRR https://arxiv.org/abs/2102.13307 db/journals/corr/corr2102.html#abs-2102-13307

Gabriele Cimolino François Rivest Latent Time-Adaptive Drift-Diffusion Model. 2021 abs/2106.02742 CoRR https://arxiv.org/abs/2106.02742 db/journals/corr/corr2106.html#abs-2106-02742

Shashi Suman François Rivest Ali Etemad Towards Personalization of User Preferences in Partially Observable Smart Home Environments. 2021 abs/2112.00971 CoRR https://arxiv.org/abs/2112.00971 db/journals/corr/corr2112.html#abs-2112-00971

François Rivest Richard Kohar A New Timing Error Cost Function for Binary Time Series Prediction. 174-185 2020 31 IEEE Trans. Neural Networks Learn. Syst. 1 https://doi.org/10.1109/TNNLS.2019.2900046 https://www.wikidata.org/entity/Q62488854 db/journals/tnn/tnn31.html#RivestK20

Rene Sturgeon François Rivest Automatic Policy Decomposition through Abstract State Space Dynamic Specialization. 1-7 2020 IJCNN https://doi.org/10.1109/IJCNN48605.2020.9207473 conf/ijcnn/2020 db/conf/ijcnn/ijcnn2020.html#SturgeonR20 Mohammed Gasmallah Farhana H. Zulkernine François Rivest Parvin Mousavi Alireza Sedghi Fully End-To-End Super-Resolved Bone Age Estimation. 498-504 2019 Canadian AI https://doi.org/10.1007/978-3-030-18305-9_51 conf/ai/2019 db/conf/ai/ai2019.html#GasmallahZRMS19 Jason T. Lam François Rivest Jean Berger Deep Reinforcement Learning for Multi-satellite Collection Scheduling. 184-196 2019 TPNC https://doi.org/10.1007/978-3-030-34500-6_13 conf/tpnc/2019 db/conf/tpnc/tpnc2019.html#LamRB19 Michael R. Kellman François Rivest Alina Pechacek Lydia Sohn Michael Lustig Barker-Coded node-pore resistive pulse sensing with built-in coincidence correction. 1053-1057 2017 ICASSP https://doi.org/10.1109/ICASSP.2017.7952317 https://www.wikidata.org/entity/Q48504833 conf/icassp/2017 db/conf/icassp/icassp2017.html#KellmanRPSL17

François Rivest John Kalaska Yoshua Bengio Conditioning and time representation in long short-term memory networks. 23-48 2014 108 Biol. Cybern. 1 https://doi.org/10.1007/s00422-013-0575-1 https://www.wikidata.org/entity/Q44931711 db/journals/bc/bc108.html#RivestKB14

Ali Sengul François Rivest Michiel van Elk Olaf Blanke Hannes Bleuler Visual and force feedback time-delays change telepresence: Quantitative evidence from crossmodal congruecy task. 577-582 2013 World Haptics https://doi.org/10.1109/WHC.2013.6548472 conf/haptics/2013 db/conf/haptics/whc2013.html#SengulREBB13

François Rivest John Kalaska Yoshua Bengio Alternative time representation in dopamine models. 107-130 2010 28 J. Comput. Neurosci. 1 https://doi.org/10.1007/s10827-009-0191-1 https://www.wikidata.org/entity/Q42461672 db/journals/jcns/jcns28.html#RivestKB10

Thomas R. Shultz François Rivest László Egri Jean-Philippe Thivierge Frédéric Dandurand Could Knowledge-Based Neural Learning be Useful in Developmental Robotics? The Case of Kbcc. 245-279 2007 4 Int. J. Humanoid Robotics 2 https://doi.org/10.1142/S0219843607001035 https://www.wikidata.org/entity/Q57090733 db/journals/ijhr/ijhr4.html#ShultzRETD07

François Rivest Thomas R. Shultz Compositionality in a Knowledge-Based Constructive Learner. 54-58 2004 AAAI Technical Report (3) https://www.aaai.org/Library/Symposia/Fall/2004/fs04-03-012.php conf/aaaifs/2004-3 db/conf/aaaifs/aaaifs2004-3.html#RivestS04 François Rivest Yoshua Bengio John Kalaska Brain Inspired Reinforcement Learning. 2004 conf/nips/2004 NIPS https://proceedings.neurips.cc/paper/2004/hash/d37b3ca37106b2bfdeaa12647e3bb1c9-Abstract.html http://papers.nips.cc/paper/2749-brain-inspired-reinforcement-learning db/conf/nips/nips2004.html#RivestBK04 1129-1136 François Rivest Doina Precup Combining TD-learning with Cascade-correlation Networks. 632-639 2003 conf/icml/2003 ICML db/conf/icml/icml2003.html#RivestP03 http://www.aaai.org/Library/ICML/2003/icml03-083.php Jean-Philippe Thivierge François Rivest Thomas R. Shultz A dual-phase technique for pruning constructive networks. 559-564 2003 IJCNN https://doi.org/10.1109/IJCNN.2003.1223407 conf/ijcnn/2003 db/conf/ijcnn/ijcnn2003.html#ThiviergeRS03 streams/conf/ijcnn

Thomas R. Shultz François Rivest Knowledge-based cascade-correlation: using knowledge to speed learning. 43-72 2001 13 Connect. Sci. 1 https://doi.org/10.1080/09540090110047767 https://www.wikidata.org/entity/Q57090735 db/journals/connection/connection13.html#ShultzR01

Thomas R. Shultz François Rivest Using Knowledge to Speed Learning: A Comparison of Knowledge-based Cascade-correlation and Multi-task Learning. 871-878 2000 conf/icml/2000 ICML db/conf/icml/icml2000.html#ShultzR00 Thomas R. Shultz François Rivest Knowledge-Based Cascade-Correlation. 641-646 2000 conf/ijcnn/2000-5 IJCNN (5) https://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.10008 db/conf/ijcnn/ijcnn2000-5.html#ShultzR00 Aman Anand Jeremy Banks Yoshua Bengio Jean Berger Olaf Blanke Hannes Bleuler Mélanie Breton Austin Carthy Sarath Chandar Abdellah Chehri Gabriele Cimolino Antoine Clavaud Frédéric Dandurand László Egri Michiel van Elk Ali Etemad Mohammed Gasmallah Alain Gosselin Masih Hashemi Isaac Hogan Jerry Huang Gwanggil Jeon John Kalaska Michael R. Kellman Behnoush Khavari Jayesh Khullar Richard Kohar Jason T. Lam Ruikang Luo Michael Lustig Ranwa Al Mallah Mariam El Mezouar Mojtaba Moattari Hussein T. Mouftah Parvin Mousavi Nilaksh Justin Norman Alina Pechacek Doina Precup Donghao Qiao Siamak Ravanbakhsh Mathieu Reymond Alex Salgo Alireza Sedghi Ali SengülAli Sengul Mehran Shakerinava Thomas R. Shultz Lydia Sohn Rene Sturgeon Shashi Suman Jean-Philippe Thivierge Konur Tholl Farhana ZulkernineFarhana H. Zulkernine