Publications

Filter by type:

Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets.
Presented at 37th Conference on Neural Information Processing Systems (NeurIPS), 2023.

Link PDF


Model-based Offline Reinforcement Learning with Local Misspecification.
Oral at 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

Link PDF


Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data.
Presented at 36th Conference on Neural Information Processing Systems (NeurIPS).
Oral at AAAI 2023 Workshop on Reinforcement Learning Ready for Production, 2023.

Link PDF


Offline Policy Optimization with Eligible Actions.
Presented at 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022.

Link PDF


SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics.
Presented at 5th Conference on Reinforcement Learning and Decision Making (RLDM), 2022.

Link PDF PDF (extended version)


Sample-Efficient Deep Reinforcement Learning for Control, Exploration and Safety.
PhD Thesis, 2021.

Link PDF


Adversarially Guided Actor-Critic.
Presented at 9th International Conference on Learning Representations (ICLR), 2021.

Link PDF


Learning Value Functions in Deep Policy Gradients using Residual Variance.
Presented at 9th International Conference on Learning Representations (ICLR), 2021.

Link PDF


Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL.
Presented at 29th International Joint Conference on Artificial Intelligence (IJCAI), 2020.

Link PDF


Temperature Decreases Spread Parameters of the New Covid-19 Case Dynamics.
Biology, 9(5), p.94, 2020.

Link PDF


MERL: Multi-Head Reinforcement Learning.
Oral at NeurIPS 2019 Workshop on Deep Reinforcement Learning, 2019.

Link PDF


High-Dimensional Control Using Generalized Auxiliary Tasks.
Research Report hal-02295705, 2019.

Link PDF


The Promise of Hierarchical Reinforcement Learning.
The Gradient, 2019.

Article


Hearables in Hearing Care: Discovering Usage Patterns Through IoT Devices.
Presented at International Conference on Universal Access in Human-Computer Interaction, 2017.

Link