Joelle Pineau

papers

1,146

total citations

papers (14)

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

ICLR 2022arXiv

257

citations

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

NEURIPS 2021arXiv

citations

Robust Policy Learning over Multiple Uncertainty Sets

ICML 2022arXiv

citations

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

ICLR 2021arXiv

citations

Regularized Inverse Reinforcement Learning

ICLR 2021arXiv

citations

Correcting Momentum in Temporal Difference Learning

ICLR 2021arXiv

citations

Learning Robust State Abstractions for Hidden-Parameter Block MDPs

ICLR 2021arXiv

citations

Online Learned Continual Compression with Adaptive Quantization Modules

ICML 2020arXiv

citations

Joelle Pineau

papers (14)

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

Language GANs Falling Short

Multi-Task Reinforcement Learning with Context-based Representations

Invariant Causal Prediction for Block MDPs

Interference and Generalization in Temporal Difference Learning

Constrained Markov Decision Processes via Backward Value Functions

Novelty Search in Representational Space for Sample Efficient Exploration

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Robust Policy Learning over Multiple Uncertainty Sets

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Regularized Inverse Reinforcement Learning

Correcting Momentum in Temporal Difference Learning

Learning Robust State Abstractions for Hidden-Parameter Block MDPs

Online Learned Continual Compression with Adaptive Quantization Modules

papers (14)

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

Language GANs Falling Short

Multi-Task Reinforcement Learning with Context-based Representations

Invariant Causal Prediction for Block MDPs

Interference and Generalization in Temporal Difference Learning

Constrained Markov Decision Processes via Backward Value Functions

Novelty Search in Representational Space for Sample Efficient Exploration

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Robust Policy Learning over Multiple Uncertainty Sets

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Regularized Inverse Reinforcement Learning

Correcting Momentum in Temporal Difference Learning

Learning Robust State Abstractions for Hidden-Parameter Block MDPs

Online Learned Continual Compression with Adaptive Quantization Modules