7 citations · 10 across the 16 of their papers we have counts for
14 papers · 1 filter
Local Sparsity Enables Unsupervised LLM Safety Detection
Xin Chen, Gil Kur, Alexander Shevchenko +1
Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks and harm categorie…
SOMBRL: Scalable and Optimistic Model-Based RL
Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza +3
We address the challenge of efficient exploration in model-based reinforcement learning (MBRL), where the system dynamics are unknown and the RL agent must learn directly from onli…
Sample-efficient and Scalable Exploration in Continuous-Time RL
Klemens Iten, Lenart Treven, Bhavya Sukhija +2
Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this pap…
Simulation Priors for Data-Efficient Deep Learning
Lenart Treven, Bhavya Sukhija, Jonas Rothfuss +3
How do we enable AI systems to efficiently learn in the real-world? First-principles models are widely used to simulate natural systems, but often fail to capture real-world comple…
Learning Safety Constraints for Large Language Models
Xin Chen, Yarden As, Andreas Krause
Large language models (LLMs) have emerged as powerful tools but pose significant safety risks through harmful outputs and vulnerability to adversarial attacks. We propose SaP, shor…
MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
Bhavya Sukhija, Stelian Coros, Andreas Krause +2
Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms u…
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
Yarden As, Bhavya Sukhija, Lenart Treven +3
Reinforcement learning (RL) is ubiquitous in the development of modern AI systems. However, state-of-the-art RL agents require extensive, and potentially unsafe, interactions with…
NeoRL: Efficient Exploration for Nonepisodic RL
Bhavya Sukhija, Lenart Treven, Florian Dörfler +2
We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single t…
When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL
Lenart Treven, Bhavya Sukhija, Yarden As +2
Reinforcement learning (RL) excels in optimizing policies for discrete-time Markov decision processes (MDP). However, various systems are inherently continuous in time, making disc…
Safe Exploration Using Bayesian World Models and Log-Barrier Optimization
Yarden As, Bhavya Sukhija, Andreas Krause
A major challenge in deploying reinforcement learning in online tasks is ensuring that safety is maintained throughout the learning process. In this work, we propose CERL, a new me…
Transductive Active Learning: Theory and Applications
Jonas Hübotter, Bhavya Sukhija, Lenart Treven +2
We study a generalization of classical active learning to real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, w…
Active Few-Shot Fine-Tuning
Jonas Hübotter, Bhavya Sukhija, Lenart Treven +2
We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance o…
Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning
Arjun Bhardwaj, Jonas Rothfuss, Bhavya Sukhija +4
We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics. PACOH-RL meta-learns…
Efficient Exploration in Continuous-time Model-based Reinforcement Learning
Lenart Treven, Jonas Hübotter, Bhavya Sukhija +2
Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model-ba…