Joelle Pineau

Position: On the Societal Impact of Open Foundation Models ICML 2024 Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning ICLR 2024 New Insights on Reducing Abrupt Representation Change in Online Continual Learning ICLR 2022 The Curious Case of Absolute Position Embeddings EMNLP 2022 Improving Passage Retrieval with Zero-Shot Question Generation EMNLP 2022 Block Contextual MDPs for Continual Learning L4DC 2022 Robust Policy Learning over Multiple Uncertainty Sets ICML 2022 A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions AAAI 2022 Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little EMNLP 2021 UnNatural Language Inference IJCNLP 2021 Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs NIPS 2021 Improving Sample Efficiency in Model-Free Reinforcement Learning from Images AAAI 2021 UnNatural Language Inference ACL 2021 Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs EACL 2021 Multi-Task Reinforcement Learning with Context-based Representations ICML 2021 Improving Reproducibility in Machine Learning Research(A Report from the NeurIPS 2019 Reproducibility Program) JMLR 2021 Sometimes We Want Ungrammatical Translations EMNLP 2021 Learning Robust State Abstractions for Hidden-Parameter Block MDPs ICLR 2021 Regularized Inverse Reinforcement Learning ICLR 2021 OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation ICML 2021 Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks IJCAI 2020 Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking AAAI 2020 Online Learned Continual Compression with Adaptive Quantization Modules ICML 2020 Stable Policy Optimization via Off-Policy Divergence Regularization UAI 2020 Learning an Unreferenced Metric for Online Dialogue Evaluation ACL 2020 Language GANs Falling Short ICLR 2020 Novelty Search in Representational Space for Sample Efficient Exploration NIPS 2020 Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization NIPS 2020 Interference and Generalization in Temporal Difference Learning ICML 2020 Literature Mining for Incorporating Inductive Bias in Biomedical Prediction Tasks (Student Abstract) AAAI 2020 Plan2Vec: Unsupervised Representation Learning by Latent Plans L4DC 2020 Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning JMLR 2020 Invariant Causal Prediction for Block MDPs ICML 2020 Constrained Markov Decision Processes via Backward Value Functions ICML 2020 On the interaction between supervision and self-play in emergent communication ICLR 2020 On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract) IJCAI 2020 On-Line Adaptative Curriculum Learning for GANs AAAI 2019 CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text IJCNLP 2019 Multitask Metric Learning: Theory and Algorithm AISTATS 2019 CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text EMNLP 2019 Seeded self-play for language learning EMNLP 2019 Separating value functions across time-scales ICML 2019 TarMAC: Targeted Multi-Agent Communication ICML 2019 No-Press Diplomacy: Modeling Multi-Agent Gameplay NIPS 2019 Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning NIPS 2019 Randomized Value Functions via Multiplicative Normalizing Flows UAI 2019 Leveraging exploration in off-policy algorithms via normalizing flows CORL 2019 Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks AAAI 2019 Combined Reinforcement Learning via Abstract Representations AAAI 2019 Streaming kernel regression with provably adaptive mean, variance, and regularization JMLR 2018 Temporal Regularization for Markov Decision Process NIPS 2018 Reward Estimation for Variance Reduction in Deep Reinforcement Learning CORL 2018 Extending Neural Generative Conversational Model using External Knowledge Sources EMNLP 2018 Focused Hierarchical RNNs for Conditional Sequence Processing ICML 2018 An Inference-Based Policy Gradient Method for Learning Options ICML 2018 Contextual Bandits for Adapting Treatment in a Mouse Model of de Novo Carcinogenesis MLHC 2018 Multitask Spectral Learning of Weighted Automata NIPS 2017 Piecewise Latent Variables for Neural Variational Text Processing EMNLP 2017 Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses ACL 2017 Learning Robust Features using Deep Learning for Automatic Seizure Detection MLHC 2016 Practical Kernel-Based Reinforcement Learning JMLR 2016 How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation EMNLP 2016 Generalized Dictionary for Multitask Learning with Boosting IJCAI 2016 An Expectation-Maximization Algorithm to Compute a Stochastic Factorization From Data IJCAI 2015 Methods of Moments for Learning Stochastic Languages: Unified Presentation and Empirical Comparison ICML 2014 Efficient Learning and Planning with Compressed Predictive States JMLR 2014 Modelling Sparse Dynamical Systems with Compressed Predictive State Representations ICML 2013 Maximum Mean Discrepancy Imitation Learning RSS 2013 Learning from Limited Demonstrations NIPS 2013 Bellman Error Based Feature Generation using Random Projections on Sparse Spaces NIPS 2013 On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization NIPS 2012 A Bayesian Approach for Learning and Planning in Partially Observable Markov Decision Processes JMLR 2011 Reinforcement Learning using Kernel-Based Stochastic Factorization NIPS 2011 PAC-Bayesian Model Selection for Reinforcement Learning NIPS 2010 Manifold Embeddings for Model-Based Reinforcement Learning under Partial Observability NIPS 2009 MDPs with Non-Deterministic Policies NIPS 2008 Bayes-Adaptive POMDPs NIPS 2007 Theoretical Analysis of Heuristic Search Methods for Online POMDPs NIPS 2007 Spoken Dialogue Management Using Probabilistic Reasoning ACL 2000