Doina Precup

Analytic Planning under Uncertainty with Moment Closure UAI 2026 Bootstrapping Personalized Insulin Therapy via Model-Based Reinforcement Learning: An In Silico Study AAAI 2026 Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning ICLR 2025 MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 Rejecting Hallucinated State Targets during Planning ICML 2025 Selective Unlearning via Representation Erasure Using Domain Adversarial Training ICLR 2025 Training Language Models to Self-Correct via Reinforcement Learning ICLR 2025 Adaptive Exploration for Data-Efficient General Value Function Evaluations NeurIPS 2024 Code as Reward: Empowering Reinforcement Learning with VLMs ICML 2024 Conditions on Preference Relations that Guarantee the Existence of Optimal Policies AISTATS 2024 Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning ICLR 2024 Discrete Probabilistic Inference as Control in Multi-path Environments UAI 2024 Efficient Reinforcement Learning by Discovering Neural Pathways NeurIPS 2024 Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search IJCAI 2024 Learning Successor Features the Simple Way NeurIPS 2024 Mixtures of Experts Unlock Parameter Scaling for Deep RL ICML 2024 Nash Learning from Human Feedback ICML 2024 Offline Multitask Representation Learning for Reinforcement Learning NeurIPS 2024 On learning history-based policies for controlling Markov decision processes AISTATS 2024 On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization NAACL 2024 On the Privacy of Selection Mechanisms with Gaussian Noise AISTATS 2024 Parseval Regularization for Continual Reinforcement Learning NeurIPS 2024 Policy Gradient Methods in the Presence of Symmetries and State Abstractions JMLR 2024 Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo ICLR 2024 QGFN: Controllable Greediness with Action Values NeurIPS 2024 ReactZyme: A Benchmark for Enzyme-Reaction Prediction NeurIPS 2024 A Definition of Continual Reinforcement Learning NeurIPS 2023 Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation AISTATS 2023 For SALE: State-Action Representation Learning for Deep Reinforcement Learning NeurIPS 2023 Multi-Environment Pretraining Enables Transfer to Action Limited Datasets ICML 2023 On the Challenges of Using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects AAAI 2023 Prediction and Control in Continual Reinforcement Learning NeurIPS 2023 Temporal Abstraction in Reinforcement Learning with the Successor Representation JMLR 2023 Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning AAAI 2023 When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability NeurIPS 2023 Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates ICLR 2022 Continuous MDP Homomorphisms and Homomorphic Policy Gradient NeurIPS 2022 COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation ICLR 2022 Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification ICML 2022 On the Expressivity of Markov Reward (Extended Abstract) IJCAI 2022 Policy Gradients Incorporating the Future ICLR 2022 Proving Theorems using Incremental Learning and Hindsight Experience Replay ICML 2022 Revisiting Heterophily For Graph Neural Networks NeurIPS 2022 Towards painless policy optimization for constrained MDPs UAI 2022 Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error ICML 2022 A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning NeurIPS 2021 A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation ICML 2021 Flexible Option Learning NeurIPS 2021 Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation NeurIPS 2021 Gradient Starvation: A Learning Proclivity in Neural Networks NeurIPS 2021 Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards ICML 2021 On the Expressivity of Markov Reward NeurIPS 2021 Preferential Temporal Difference Learning ICML 2021 Randomized Exploration in Reinforcement Learning with General Value Function Approximation ICML 2021 Self-Supervised Attention-Aware Reinforcement Learning AAAI 2021 Temporally Abstract Partial Models NeurIPS 2021 Variance Penalized On-Policy and Off-Policy Actor-Critic AAAI 2021 A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms AISTATS 2020 Algorithmic Improvements for Deep Reinforcement Learning Applied to Interactive Fiction AAAI 2020 An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay NeurIPS 2020 Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning AISTATS 2020 Forethought and Hindsight in Credit Assignment NeurIPS 2020 Gifting in Multi-Agent Reinforcement Learning (Student Abstract) AAAI 2020 Interference and Generalization in Temporal Difference Learning ICML 2020 Invariant Causal Prediction for Block MDPs ICML 2020 On Efficiency in Hierarchical Reinforcement Learning NeurIPS 2020 Options of Interest: Temporal Abstraction with Interest Functions AAAI 2020 Reward Propagation Using Graph Convolutional Networks NeurIPS 2020 SVRG for Policy Evaluation with Fewer Gradient Evaluations IJCAI 2020 Value-driven Hindsight Modelling NeurIPS 2020 Value Preserving State-Action Abstractions AISTATS 2020 What can I do here? A Theory of Affordances in Reinforcement Learning ICML 2020 Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks NeurIPS 2019 Combined Reinforcement Learning via Abstract Representations AAAI 2019 Connecting Weighted Automata and Recurrent Neural Networks through Spectral Learning AISTATS 2019 Hindsight Credit Assignment NeurIPS 2019 Learning Options with Interest Functions AAAI 2019 Leveraging Observations in Bandits: Between Risks and Benefits AAAI 2019 Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments CoRL 2019 Neural Transfer Learning for Cry-Based Diagnosis of Perinatal Asphyxia Interspeech 2019 Off-Policy Deep Reinforcement Learning without Exploration ICML 2019 Per-Decision Option Discounting ICML 2019 Prediction of Disease Progression in Multiple Sclerosis Patients using Deep Learning Analysis of MRI Data MIDL 2019 The Option Keyboard: Combining Skills in Reinforcement Learning NeurIPS 2019 The Termination Critic AISTATS 2019 Convergent Tree Backup and Retrace with Function Approximation ICML 2018 Learning Safe Policies with Expert Guidance NeurIPS 2018 Nonlinear Weighted Finite Automata AISTATS 2018 Temporal Regularization for Markov Decision Process NeurIPS 2018 Approximate Value Iteration with Temporally Extended Actions (Extended Abstract) IJCAI 2017 World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions EMNLP 2017 Differentially Private Policy Evaluation ICML 2016 Learning Multi-Step Predictive State Representations IJCAI 2016 Leveraging Lexical Resources for Learning Entity Embeddings in Multi-Relational Data ACL 2016 Practical Kernel-Based Reinforcement Learning JMLR 2016 Verb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms EMNLP 2016 An Expectation-Maximization Algorithm to Compute a Stochastic Factorization From Data IJCAI 2015 Basis refinement strategies for linear value function approximation in MDPs NeurIPS 2015 Data Generation as Sequential Decision Making NeurIPS 2015 Variational Generative Stochastic Networks with Collaborative Shaping ICML 2015 A new Q(lambda) with interim forward view and Monte Carlo equivalence ICML 2014 Iterative Multilevel MRF Leveraging Context and Voxel Information for Brain Tumour Segmentation in MRI CVPR 2014 Learning with Pseudo-Ensembles NeurIPS 2014 Optimizing Energy Production Using Policy Search and Predictive State Representations NeurIPS 2014 Sample-based approximate regularization ICML 2014 Average Reward Optimization Objective In Partially Observable Domains ICML 2013 Bellman Error Based Feature Generation using Random Projections on Sparse Spaces NeurIPS 2013 Learning from Limited Demonstrations NeurIPS 2013 On Average Reward Policy Evaluation in Infinite-State Partially Observable Systems AISTATS 2012 On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization NeurIPS 2012 Value Pursuit Iteration NeurIPS 2012 Reinforcement Learning using Kernel-Based Stochastic Factorization NeurIPS 2011 A Study of Approximate Inference in Probabilistic Relational Models ACML 2010 Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation NeurIPS 2009 Bounding Performance Loss in Approximate MDP Homomorphisms NeurIPS 2008