publications
2026
-
-
Reinforcement Learning via Self-DistillationarXiv, 2026 -
TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement LearningOral @ International Conference on Learning Representations, 2026 -
Optimistic Task Inference for Behavior Foundation ModelsOral @ International Conference on Learning Representations, 2026
2025
-
Test-time Offline Reinforcement Learning on Goal-related ExperienceEuropean Workshop in Reinforcement Learning, 2025 -
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement LearningAdvances in Neural Information Processing Systems, 2025 -
Active Fine-Tuning of Generalist PoliciesInternational Conference on Machine Learning, 2025 -
Zero-shot Offline Imitation Learning via Optimal TransportInternational Conference on Machine Learning, 2025 -
Directed Exploration in Reinforcement Learning from Linear Temporal LogicTransactions on Machine Learning Research, J2C Track, 2025
2024
-
Problem Space Transformations for Generalisation in Behavioural CloningCoRL Workshop on Safe and Robust Robot Learning for Operation in the Real World, 2024 -
Modelling Microbial Communities with Graph Neural NetworksInternational Conference on Machine Learning, 2024 -
Causal Action Influence Aware Counterfactual Data AugmentationInternational Conference on Machine Learning, 2024
2023
-
Goal-conditioned Offline Planning from Curious ExplorationAdvances in Neural Information Processing Systems, 2023 -
Efficient Learning of High Level Plans from PlayInternational Conference on Robotics and Automation, 2023
2022
-
SFP: State-free Priors for Exploration in Off-Policy Reinforcement LearningTransactions on Machine Learning Research, 2022
2021
-
Planning from Pixels in Environments with Combinatorially Hard Search SpacesAdvances in Neural Information Processing Systems, 2021