ÀŠ°óSMÉçÇű
Prof. Joelle Pineau belongs to the School of Computer Science and is director of the Reasoning and Learning Lab at CIM.
2023
C.Y. Su, S. Zhou, E. Gonzalez-Kozlova, G. Butler-Laporte (âŠ.) J. Pineau, V. Mooser, T. Marron, N.D. Beckmann, S. Kim-Schulze, A.W. Charney, S. Gnjatic, D.E. Kaufmann, M. Merard, J.B. Richards. âCirculating proteins to predict COVID-19 severityâ. Scientific Reports 13 (1), 6236. 2023.
H. Satija, A. Lazaric, M. Pirotta, J. Pineau. âGroup Fairness in Reinforcement Learningâ. Transactions on Machine Learning Research. pp.1-60. 2023.
D.S. Sachan, M. Lewis, D. Yogatama, L. Zettlemoyer, J. Pineau, M. Zaheer. âQuestions Are All You Need to Train a Dense Passage Retrieverâ. Transactions of the Association for Computational Linguistics 11, 600-616. 2023.
M.A. Legault, J. Hartford, M. Lu, A.Y. Yang, J. Pineau. âEvaluating machine learning instrumental variable methods to estimate conditional treatment effects in Mendelian randomizationâ. International Genetic Epidemiology Society. 2023.
P. Henderson, J. Hu, M. Diab, J. Pineau. âRethinking Machine Learning Benchmarks in the Context of Professional Codes of Conductâ. Third ACM Symposium on Computer Science and Law (CSLAW 2024).
M. Wabartha, J. Pineau. âPiecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learningâ. NeurIPS workshop on XAI in Action: Past, Present, and Future Applications. 2023.
2022
Madhulika Srikumar et al. âAdvancing ethics review practices in AI researchâ. In: Nature Machine Intelligence 4.12 (2022), pp. 1061â 1064.
Devendra Singh Sachan et al. âQuestions are all you need to train a dense passage retrieverâ. In: Transactions of the Association for Computational Linguistics 11 (2023), pp. 600â616.
Devendra Sachan et al. âImproving Passage Retrieval with Zero-Shot Question Generationâ. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022, pp. 3781â3797.
Bogdan Mazoure et al. âLow-Rank Representation of Reinforcement Learning Policiesâ. In: Journal of Artificial Intelligence Research 75 (2022), pp. 597â636.
GX-Chen Anthony et al. âA Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictionsâ. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 36. 6. 2022, pp. 6829â6837.
Ekaterina Kochmar et al. âAutomated datadriven generation of personalized pedagogical interventions in intelligent tutoring systemsâ. In: International Journal of Artificial Intelligence in Education 32.2 (2022), pp. 323â349.
Lucas Caccia et al. âNew Insights on Reducing Abrupt Representation Change in Online Continual Learningâ. In: International Conference on Learning Representations. 2021.
Martin Cousineau et al. âEstimating causal effects with optimization-based methods: A review and empirical comparisonâ. In: European Journal of Operational Research 304.2 (2023), pp. 367â380.
2021
J. Pineau, P. Vincent-Lamarre, K. Sinha, V. LariviĂšre, A. Beygelzimer, F. DâAlche-Buc, E. Fox, and H. Larochelle. âImproving reproducibility in machine learning research: a report from the NeurIPS 2019 reproducibility program,â Journal of Machine Learning Research 22. 2021.p.1-20
E. Kochmar, D.D. Vu, R. Belfer, V. Gupta, I.V. Serban, and J. Pineau. âAutomated Data-Driven Generation of Personalized Pedagogical Interventions in Intelligent Tutoring Systems,â International Journal of Artificial Intelligence in Education, 2021, 1-27
H. Satija, P.S. Thomas, J. Pineau, and R. Laroche. âMulti-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs,â Advances in Neural Information Processing Systems (NeurIPS) 2021
J. Lee, W. Jeon, B. Lee, J. Pineau, and K.E. Kim. âOptidice: Offline policy optimization via stationary distribution correction estimation,â International Conference on Machine Learning (ICML), 2021, 6120-6130
S. Sodhani, A. Zhang, and J. Pineau. âMultitask reinforcement learning with context-based representations,â International Conference on Machine Learning (ICML), 2021, 9767-9779
K. Sinha, P. Parthasarathi, J. Pineau, and A. Williams. âUnnatural language inference,â Annual Meeting of the Association for Computational Linguistics (ACL). 2021. Outstanding Paper Award.
P. Parthasarathi, J. Pineau, and S. Chandar. âDo Encoder Representations of Generative Dialogue Models have sufficient summary of the Information about the task?,â Special Interest Group on Discourse and Dialogue (SigDial). 2021.
P. Parthasarathi, M. Abdelsalam, J. Pineau, and S. Chandar. âA Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss,â Special Interest Group on Discourse and Dialogue (SigDial). 2021
J. Romoff, P. Henderson, D. Kanaa, E. Bengio, A. Touati, P.L. Bacon, and J. Pineau. âTDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?,â International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2021
P. Parthasarathi, K. Sinha, J. Pineau, and A. Williams. âSometimes we want ungrammatical translations,â Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021
K. Sinha, R. Jia, D. Hupkes, J. Pineau, A. Williams, and D. Kiela. âOrder word matters pre-training for little,â Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021
D. Jambor, K. Teru, J. Pineau, and W.L. Hamilton. âExploring the Limits of Few-Shot Link Prediction in Knowledge Graphs,â European Chapter of the Association for Computational Linguistics (EACL). 2021.
S. Delacroix, J. Pineau, and J. Montgomery. âDemocratising the digital revolution: the role of data governance,â Book chapter in Reflections on AI for Humanity, Braunschweig & Ghallab (eds.), Springer, 2021. 40-52. Accepted, to appear in 2022
M. Cousineau, V. Verter, S.A. Murphy, and J. Pineau. âEstimating Causal Effects with Optimization-Based Methods: A Review and Empirical Comparison,â European Journal of Operational Research 2022.
L. Caccia, R. Aljundi, N. Asadi, T. Tuytelaars, J. Pineau, and E. Belilovsky. âNew Insights on Reducing Abrupt Representation Change in Online Continual Learning,â International Conference on Learning Representations 2022
A. GX-Chen, V. Chelu, B.A. Richards, and J. Pineau. âA Generalized Bootstrap Target for Value- Learning, Efficiently Combining Value and Feature Predictions,â American Associate for Artificial Page 44 CIM 2021 Annual Report CIM 2021 Annual Report Page 45 Intelligence (AAAI) 2021.
L. Caccia, R. Aljundi, N. Asadi, T. Tuytelaars, J. Pineau, and E. Belilovsky. âReducing representation drift in online continual learning,â arXiv preprint arXiv:2104.05025
K. Bullard, D. Kiela, F. Meier, J. Pineau, and J. Foerster. âQuasi-equivalence discovery for zeroshot emergent communication,â arXiv preprint arXiv:2103.08067
C. Lyle, A. Zhang, M. Jiang, J. Pineau, and Y. Gal. âResolving Causal Confusion in Reinforcement Learning via Robust Exploration,â Self-Supervision for Reinforcement Learning Workshop-ICLR 2021
M. Tomar, A. Zhang, R. Calandra, M.E. Taylor, and J. Pineau. âModel-invariant state abstractions for model-based reinforcement learning,â arXiv preprint arXiv:2102.09850
B. Li, V. François-Lavet, T. Doan, and J. Pineau. âDomain adversarial reinforcement learning,â arXiv preprint arXiv:2102.07097
A. Sriram, M. Muckley, K. Sinha, F. Shamout, J. Pineau, K.J. Geras, L. Azour, Y. Aphinyanaphongs, N. Yakubova, and W. Moore. âCovid-19 prognosis via self-supervised representation learning and multiimage prediction,â arXiv preprint arXiv:2101.04909
C.Y. Su, S. Zhou, E. Gonzalez-Kozlova, G. Butler- Laporte, (...) J. Pineau (...) and B. Richards. âCirculating proteins to predict adverse COVID-19 outcomes,â medRxiv. . org/10.1101/2021.10.04.21264015
2020
Benjamin Haibe-Kains, George Alexandru Adam, Ahmed Hosny, Farnoosh Khodakarami, MAQC Board, Levi Waldron, Bo Wang, Chris McIntosh, Anshul Kundaje, Casey S Greene, Michael M Hoffman, Jeffrey T Leek, Wolfgang Huber, Alvis Brazma, Joelle Pineau, Robert Tibshirani, Trevor Hastie, John Ioannidis, John Quackenbush, Hugo JWL Aerts. The importance of transparency and reproducibility in artificial intelligence research. Nature. 2020.
Nathan Peifer-Smadja, Redwan Maatoug, François-Xavier Lescure, Eric DâOrtenzio, Joelle Pineau and Jean-RĂ©mi King. Machine Learning for COVID-19 needs global collaboration and data-sharing. Nature Machine Intelligence. 2020.
Vincenzo Forgetta, Julyan Keller-Baruch, Marie Forest, Audrey Durand, Sahir Bhatnagar, John P Kemp, Maria Nethander, Daniel Evans, John A Morris, Douglas P Kiel, Fernando Rivadeneira, Helena Johansson, Nicholas C Harvey, Dan Mellström, Magnus Karlsson, Cyrus Cooper, David M Evans, Robert Clarke, John A Kanis, Eric Orwoll, Eugene V McCloskey, Claes Ohlsson, Joelle Pineau, William D Leslie, Celia MT Greenwood, J Brent Richards. Development of a polygenic risk score to improve screening for fracture risk: A genetic risk prediction study. PLoS medicine 17 (7). 2020.
Ximeng Mao, Joelle Pineau, Roy Keyes, Shirin A Enger. RapidBrachyDL: Rapid Radiation Dose Calculations in Brachytherapy via Deep Learning. International Journal of Radiation Oncology Biology Physics. 2020
Peter Henderson, Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, Joelle Pineau. Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning. JMLR. 21(248), pp.1â43.
Koustuv Sinha, Joelle Pineau, Jessica Forde, Rosemary Nan Ke, Hugo Laorchelle. Neurips 2019 Reproducibility Challenge. A special issue of the journal ReScience C 6(2). 2020.
Clare Lyle, Amy Zhang, Angelos Filos, Shagun Sodhani, Marta Kwiatkowska, Yarin Gal, Doina Precup, Joelle Pineau. Invariant Causal Prediction for Block MDPs. ICML 2020.
Harsh Satija, Philip Amortila, Joelle Pineau. Constrained Markov Decision Processes via Backward Value Functions. ICML 2020.
Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Joelle Pineau. Online Learned Continual Compression with Adaptive Quantization Module. ICML 2020.
Emmanuel Bengio, Joelle Pineau, Doina Precup. Interference and Generalization in Temporal Difference Learning. Submitted and accepted to ICML 2020.
Maxime Wabartha, Audrey Durand, Vincent François-Lavet, Joelle Pineau. Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks. IJCAI 2020.
Ahmed Touati, Amy Zhang, Joelle Pineau, Pascal Vincent. Stable Policy Optimization via Off-Policy Divergence Regularization. UAI 2020.
Koustuv Sinha, Prasanna Parthasarathi, Jasmine Wang, Ryan Lowe, William L Hamilton, Joelle Pineau. Learning an Unreferenced Metric for Online Dialogue Evaluation. ACL 2020.
Ge Yang, Amy Zhang, Ari Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra. Plan2Vec: Unsupervised Representation Learning by Latent Plans. Learning for Dynamics and Control (L4DC) 2020.
Iulian Vlad Serban, Varun Gupta, Ekaterina Kochmar, Dung D Vu, Robert Belfer, Joelle Pineau, Aaron Courville, Laurent Charlin, Yoshua Bengio. A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM. AIED 2020.
Ekaterina Kochmar, Dung D Vu, Robert Belfer, Varun Gupta, Iulian V Serban, Joelle Pineau. Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System. AIED 2020.
R.Y. (David) Tao, Vincent Francois-Lavet, Joelle Pineau. Novelty Search in Representational Space for Sample Efficient Exploration. NeurIPS 2020. Oral presentation (1% of submissions).
Paul Barde, Julien Roy, Wonseok Jeon, Joelle Pineau, Chris Pal, Derek Nowrouzezahrai. Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization. NeurIPS 2020. Spotlight presentation (4% of submissions).
2019
I.V. Serban, C. Sankar, M. Pieped, J. Pineau, Y. Bengio. âThe Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approachâ. Journal of Machine Learning Research (JMLR). Accepted.
V. François-Lavet, G. Rabusseau, J. Pineau, D. Ernst, R. Fontaineau. âOn Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observabilityâ. Journal of AI Research (JAIR). Vol.65. pp.1-30. 2019.
A.M.Froomkin, I. Kerr, J. Pineau. âWhen AIs outperform doctors: Confronting the challenges of a tort-induced over-reliance on machine learningâ. Arizona Law Review, vol.61:33. 2019.
P. Paquette, Y. Lu, S. Bocco, M.O. Smith, S. Ortiz-Gagne, J. K. Kummerfeld, S. Singh, J. Pineau, A. Courville. âNo Press Diplomacy: Modeling Multi-Agent Gameplayâ. NeurIPS 2019.
M. Assran, J. Romoff, N. Ballas, J. Pineau, M. Rabbat. âGossip-based Actor-Learner Architectures for Deep Reinforcement Learningâ. NeurIPS 2019.
J. Romoff, P. Henderson, A. Touati, E. Brunskill, J. Pineau, Y. Ollivier, âSeparable value functions across time-scalesâ. ICML 2019.
A. Das, T. Gervet, J. Romoff, D. Batra, D. Parikh, M. Rabbat, J. Pineau, âTarMAC: Targeted Multi-Agent Communicationâ. ICML 2019.
K. Sinha, S. Sodhani, J. Dong, J. Pineau, W. L. Hamilton. âCLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textâ. EMNLP 2019.
B. Mazoure, T. Doan, A. Durand, R.D. Helm, J. Pineau. âLeveraging exploration in off-policy algorithms via normalizing flowsâ. CoRL 2019
L. Caccia, H. van Hoof, A. Courville, J. Pineau. âDeep Generative Modeling of LiDAR Dataâ. IROS 2019.
R. Lowe, J. Foerster, Y-L. Boureau, J. Pineau, Y. Dauphin. âOn the Pitfalls of Measuring Emergent Communicationâ. AAMAS 2019.
J. Pineau, K. Sinha, G. Fried, R.N. Ke, H. Larochelle (guest editors). ReScience Journal, vol.5(2). Special Issue on the ICLR Reproducibility Challenge 2019.
2018
V. Francois-Lavet, P. Henderson, R. Islam, M. Bellemare, J. Pineau. "An Introduction to Deep Reinforcement Learningâ. Foundations and Trends in Machine Learning. 11 (3-4). pp.219-354. 2018.
I. V. Serban, R. Lowe, P. Henderson, L. Charlin, J. Pineau. "A Survey of Available Corpora for Building Data-Driven Dialogue Systems: The Journal Versionâ. Dialogue & Discourse. 9 (1). pp.1-49. 2018.
A. Durand, O. Maillard, J. Pineau. "Streaming kernel regression with provably adaptive mean, variance, and regularizationâ. Journal of Machine Learning Research. 19. pp.1-34. 2018.
P. Henderson,R. Islam, P. Bachman, J. Pineau, D. Precup, D. Meger."Deep Reinforcement Learning that Mattersâ. AAAI. 7 pages. 2018.
P. Henderson, W-D. Chang, P.L. Bacon, D. Meger, J. Pineau, D. Precup. "OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learningâ. AAAI. 7 pages. 2018.
P. Henderson, K. Sinha, N. Angelard-Gontier, N.R. Ke, G. Fried, R. Lowe, J. Pineau. "Ethical Challenges in Data-Driven Dialogue Systemsâ. AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society. 7 pages. 2018.
M. Smith, H. van Hoof, J. Pineau. "An Inference-Based Policy Gradient Method for Learning Optionsâ. ICML. 8 pages. 2018.
A. Durand, C. Achilleos, D. Iacovides, K. Strati, T. Mitsis, J. Pineau. "Contextual Bandits for Adapting Treatment in a Mouse Model of de Novo Carcinogenesisâ. Machine Learning for Healthcare. pp.67-82 2018.
P. Thodoro, A. Durand, J. Pineau, D. Precup. "Temporal Regularization for Markov Decision Processesâ. NeurIPS (formerly NIPS). 8 pages. 2018.
P. Parthasarathi, J. Pineau. "Extending Neural Generative Conversational Model using External Knowledge Sourcesâ. EMNLP. 6 pages. 2018.
J. Romo, P. Henderson, A. Piche, V. Francois-Lavet, J. Pineau. "Reward Estimation forVariance Reduction in Deep Reinforcement Learningâ. International Conference on Robot Learning (CoRL). 11 pages. 2018.
P. Henderson, J. Romo, J. Pineau. "Where Did My OptimumGo?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methodsâ. EWRL. 2018.
A. Touati, H. Satija, J. Romo, J. Pineau, P. Vincent. "Randomized Value Functions via Multiplicative Normalizing Flowsâ. 8 pages. EWRL. 2018.
2017
M. Ghorbel, J. Pineau, R. Gourdeau, S. Javdani, S. Srinivasa. âA Decision-Theoretic Approach for the Collaborative Control of a Smart Wheelchairâ. In. Journal of Social Robotics. pp. 1-15. 2017.
R. Lowe, N. Pow, I.V. Serban, L. Charlin, C-W. Liu J. Pineau. âTraining end-to-end dialogue systems with the ubuntu dialogue corpusâ. In. Dialogue & Discourse. pp. 31-65. 2017.
A. Emami, J El Youssef, R Rabasa-Lhoret, J Pineau, JR Castle, A Haidar. âModeling Glucagon Action in Patients with Type 1 Diabetesâ. IEEE journal of biomedical and health informatics 21 (4), 1163-1171. 2017.
W. Choi, O. Cyens, T. Chan, M. Schijven, S. Lajoie, M.E. Mancini, P. Dev, L. Fellander-Tsai, M. Ferland, P. Kato, J. Lau, M. Montonaro, J. Pineau, R. Aggarwal. âEngagement and Learning in Simulation: Recommendations of the Simnovate Engaged Learning Domain Groupâ. BMJ Simulation & Technology Enhanced Learning. 2017
R. Lowe, M. Noseworthy, I.V. Serban, N. Angelard-Gontier, E. Bengio, J. Pineau. âTowards an Automatic Turing Test: Learning to Evaluate Dialogue Responsesâ. Association for Computational Linguistics (ACL). 2017. Outstanding paper track (1.5% of submissions).
G. Rabusseau, B. Balle, J. Pineau. âMultitask Spectral Learning of Weighted Automataâ. Neural Information Processing Systems (NIPS). 2017.
D. Bahdanau, P. Brakel, K. Xu, A. Goyal, R. Lowe, J. Pineau, A. Courville, Y. Bengio. âAn Actor-Critic Algorithm for Sequence Predictionâ. International Conference on Learning Representations (ICLR). 2017.
I.V. Serban, A. Sordoni, R. Lowe, L. Charlin, J. Pineau, A. Courville, Y. Bengio.âA Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguesâ. Association for the Advancement of Artificial Intelligence (AAAI). 2017.
I.V. Serban, R. Lowe, L. Charlin, J. Pineau. âGenerative Deep Neural Networks for Dialogue: A Short Reviewâ. Empirical Methods in Natural Language Processing (EMNLP). 2017.
I.V. Serban, A.G. Ororbia II, J. Pineau, A. Courville. âPiecewise Latent Variables for Neural Variational Text Processingâ. Empirical Methods in Natural Language Processing (EMNLP). 2017.
M. Noseworthy, J.C.K. Cheung, J. Pineau. âPredicting Success in Goal-Driven Human-Human Dialoguesâ. SIGdial Meeting on Discourse and Dialogue (SIGdial). 2017.
H.P. Truong, P. Parthasarathi, J. Pineau. âMACA: A Modular Architecture for Conversational Agentsâ. SIGdial Meeting on Discourse and Dialogue (SIGDIAL). 2017.
M. Smith, L. Charlin, J. Pineau. âA Sparse Probabilistic Model of User Preference Dataâ. Canadian Conference on Artificial Intelligence (CAIAC). 2017.
E. Bengio, V. Thomas, J. Pineau, D. Precup, Y. Bengio. âIndependently Controllable Featuresâ Reinforcement Learning and Decision Making (RLDM). arXiv: 1708.01289. 2017.
I.V. Serban, C. Sankar, M. Germain, S. Zhang, Z. Lin, S. Subramanian, T. Kim, M. Pieper, S. Chandar, N. Ke, S. Rajeswar, A. Brebisson, J.M.R. Sotelo, D. Suhubdy, V. Michalski, A. Nguyen, J. Pineau, Y. Bengio. âA Deep Reinforcement Learning Chatbot (Short Version)â. Neural Information Processing Systems (NIPS) Workshop on Conversational AI. 2017.
X. Cao, G. Rabusseau, J. Pineau. âTensor Regression Networks with various Low-Rank Tensor Approximations. arXiv: 1712.09520. 2017.
A. Goyal, N.R. Ke, A. Lamb, C. Pal, J. Pineau, Y. Bengio. âACtuAL: Actor-Critic Under Adversarial Learningâ arXiv: 1711.04755. 2017.
A. Durand, O-A. Maillard, J. Pineau. âStreaming kernel regression with provably adaptive mean, variance, and regularizationâ arXiv: 1708.00768. 2017.
P. Henderson,R. Islam, P. Bachman, J. Pineau, D. Precup, D. Meger.âDeep Reinforcement Learning that Mattersâ. arXiv: 1709.06560. (Accepted at AAAI 2018.)
P. Henderson, W-D. Chang, P.L. Bacon, D. Meger, J. Pineau, D. Precup. âOptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learningâ. arXiv: 1709.06683. (Accepted at AAAI 2018.)
P. Henderson, K. Sinha, N. Angelard-Gontier, N.R. Ke, G. Fried, R. Lowe, J. Pineau. âEthical Challenges in Data-Driven Dialogue Systemsâ. arXiv: 1711.09050. (Accepted at AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society. 2018.)