activity
20212025
most citedRisk-Averse Offline Reinforcement Learning

15 citations · 15 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2025

Epistemically-guided forward-backward exploration

Núria Armengol Urpí, Marin Vlastelica, Georg Martius +1

Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward repres…

cs.RO2025

CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation

Yuanchen Yuan, Jin Cheng, Núria Armengol Urpí +1

Enabling legged robots to perform non-prehensile loco-manipulation is crucial for enhancing their versatility. Learning behaviors such as whole-body object pushing often requires s…

cs.LG2024

Causal Action Influence Aware Counterfactual Data Augmentation

Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica +1

Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demons…

cs.LG2023

Efficient Learning of High Level Plans from Play

Núria Armengol Urpí, Marco Bagatella, Otmar Hilliges +2

Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goa…

cs.LG2021★ 15 cited

Risk-Averse Offline Reinforcement Learning

Núria Armengol Urpí, Sebastian Curi, Andreas Krause

Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. Thus, the agent can only use data previo…