15 citations · 63 across the 13 of their papers we have counts for
14 papers
Get Back Here: Robust Imitation by Return-to-Distribution Planning
Geoffrey Cideron, Baruch Tabanpour, Sebastian Curi +6
We consider the Imitation Learning (IL) setup where expert data are not collected on the actual deployment environment but on a different version. To address the resulting distribu…
Safe Reinforcement Learning via Confidence-Based Filters
Sebastian Curi, Armin Lederer, Sandra Hirche +1
Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems. We develop confidence-based safety filters, a control-theoretic approach fo…
Gradient-Based Trajectory Optimization With Learned Dynamics
Bhavya Sukhija, Nathanael Köhler, Miguel Zamora +4
Trajectory optimization methods have achieved an exceptional level of performance on real-world robots in recent years. These methods heavily rely on accurate analytical models of…
Constrained Policy Optimization via Bayesian World Models
Yarden As, Ilnura Usmanova, Sebastian Curi +1
Improving sample-efficiency and safety are crucial challenges when deploying reinforcement learning in high-stakes real world applications. We propose LAMBDA, a novel model-based a…
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
Sebastian Curi, Ilija Bogunovic, Andreas Krause
In real-world tasks, reinforcement learning (RL) agents frequently encounter situations that are not present during training time. To ensure reliable performance, the RL agents nee…
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…
Logistic Q-Learning
Joan Bas-Serrano, Sebastian Curi, Andreas Krause +1
We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The method is closely related to the classic…
Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory
Lenart Treven, Sebastian Curi, Mojmir Mutny +1
The principal task to control dynamical systems is to ensure their stability. When the system is unknown, robust approaches are promising since they aim to stabilize a large set of…
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
Sebastian Curi, Felix Berkenkamp, Andreas Krause
Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often attributed to their ability to…
Adaptive Sampling for Stochastic Risk-Averse Learning
Sebastian Curi, Kfir. Y. Levy, Stefanie Jegelka +1
In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples. To address this, we consider the pr…
Structured Variational Inference in Unstable Gaussian Process State Space Models
Silvan Melchior, Sebastian Curi, Felix Berkenkamp +1
We propose a new variational inference algorithm for learning in Gaussian Process State-Space Models (GPSSMs). Our algorithm enables learning of unstable and partially observable s…
Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning
Marcello Fiducioso, Sebastian Curi, Benedikt Schumacher +2
We tune one of the most common heating, ventilation, and air conditioning (HVAC) control loops, namely the temperature control of a room. For economical and environmental reasons,…
Online Variance Reduction with Mixtures
Zalán Borsos, Sebastian Curi, Kfir Y. Levy +1
Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction. In this work, we propose a new framewo…
Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations
Sebastian Curi, Kfir Y. Levy, Andreas Krause
We address the problem of estimating the inputs of a dynamical system from measurements of the system's outputs. To this end, we introduce a novel estimation algorithm that explici…