319 citations · 1.2k across the 28 of their papers we have counts for
30 papers
Kolibri: A Sovereign European Model on the Pareto Frontier
Aleph Alpha, :, Moritz Althaus +65
This report introduces Kolibri, an English-German mixture-of-experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under t…
A Family of LLMs Liberated from Static Vocabularies
Aleph Alpha, :, Adnen Abdessaied +35
Tokenization is a central component of natural language processing in current large language models (LLMs), enabling models to convert raw text into processable units. Although lea…
Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability
Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska +2
Optimal decision-making under partial observability requires reasoning about the uncertainty of the environment's hidden state. However, most reinforcement learning architectures h…
Information-Theoretic Safe Bayesian Optimization
Alessandro G. Bottero, Carlos E. Luis, Julia Vinogradska +2
We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an a~priori unknown (safety) constraint.…
Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization
Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska +2
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance ov…
Scalable Meta-Learning with Gaussian Processes
Petru Tighineanu, Lukas Grossberger, Paul Baireuther +4
Meta-learning is a powerful approach that exploits historical data to quickly solve new tasks from the same distribution. In the low-data regime, methods based on the closed-form p…
Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning
Melrose Roderick, Gaurav Manek, Felix Berkenkamp +1
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the lear…
Value-Distributional Model-Based Reinforcement Learning
Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska +2
Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcemen…
MALIBO: Meta-learning for Likelihood-free Bayesian Optimization
Jiarong Pan, Stefan Falkner, Felix Berkenkamp +1
Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged a…
Model-Based Uncertainty in Value Functions
Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska +2
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance ov…
Information-Theoretic Safe Exploration with Gaussian Processes
Alessandro G. Bottero, Carlos E. Luis, Julia Vinogradska +2
We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an a priori unknown (safety) constraint. A common approach is to place a…
Transfer Learning with Gaussian Processes for Bayesian Optimization
Petru Tighineanu, Kathrin Skubch, Paul Baireuther +3
Bayesian optimization is a powerful paradigm to optimize black-box functions based on scarce and noisy data. Its data efficiency can be further improved by transfer learning from r…
On-Policy Model Errors in Reinforcement Learning
Lukas P. Fröhlich, Maksym Lefarov, Melanie N. Zeilinger +1
Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods…
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…
Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
Noah Y. Siegel, Jost Tobias Springenberg, Felix Berkenkamp +6
Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience…
Safe Exploration for Interactive Machine Learning
Matteo Turchetta, Felix Berkenkamp, Andreas Krause
In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active…
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…
Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning
Torsten Koller, Felix Berkenkamp, Matteo Turchetta +2
Reinforcement learning has been successfully used to solve difficult tasks in complex unknown environments. However, these methods typically do not provide any safety guarantees du…
No-Regret Bayesian Optimization with Unknown Hyperparameters
Felix Berkenkamp, Angela P. Schoellig, Andreas Krause
Bayesian optimization (BO) based on Gaussian process models is a powerful paradigm to optimize black-box functions that are expensive to evaluate. While several BO algorithms prova…
Information-Directed Exploration for Deep Reinforcement Learning
Nikolay Nikolov, Johannes Kirschner, Felix Berkenkamp +1
Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is…
Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy
Robin Spiess, Felix Berkenkamp, Jan Poland +1
The energy output of photovoltaic (PV) power plants depends on the environment and thus fluctuates over time. As a result, PV power can cause instability in the power grid, in part…
The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
Spencer M. Richards, Felix Berkenkamp, Andreas Krause
Learning algorithms have shown considerable prowess in simulation by allowing robots to adapt to uncertain environments and improve their performance. However, such algorithms are…
Learning-based Model Predictive Control for Safe Exploration
Torsten Koller, Felix Berkenkamp, Matteo Turchetta +1
Learning-based methods have been successful in solving complex control tasks without significant prior knowledge about the system. However, these methods typically do not provide a…
Verifying Controllers Against Adversarial Examples with Bayesian Optimization
Shromona Ghosh, Felix Berkenkamp, Gireeja Ranade +2
Recent successes in reinforcement learning have lead to the development of complex controllers for real-world robots. As these robots are deployed in safety-critical applications a…