382 citations · 1.2k across the 106 of their papers we have counts for
42 papers · 1 filter
Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning
Pascal Klink, Florian Wolf, Kai Ploeger +2
Reinforcement Learning (RL) allows learning non-trivial robot control laws purely from data. However, many successful applications of RL have relied on ad-hoc regularizations, such…
Sampling-Free Probabilistic Deep State-Space Models
Andreas Look, Melih Kandemir, Barbara Rakitsch +1
Many real-world dynamical systems can be described as State-Space Models (SSMs). In this formulation, each observation is emitted by a latent state, which follows first-order Marko…
On the Benefit of Optimal Transport for Curriculum Reinforcement Learning
Pascal Klink, Carlo D'Eramo, Jan Peters +1
Curriculum reinforcement learning (CRL) allows solving complex tasks by generating a tailored sequence of learning tasks, starting from easy ones and subsequently increasing their…
How Crucial is Transformer in Decision Transformer?
Max Siebenborn, Boris Belousov, Junning Huang +1
Decision Transformer (DT) is a recently proposed architecture for Reinforcement Learning that frames the decision-making process as an auto-regressive sequence modeling problem and…
Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes
Joe Watson, Jan Peters
Monte Carlo methods have become increasingly relevant for control of non-differentiable systems, approximate dynamics models and learning from data. These methods scale to high-dim…
Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images
Bang You, Oleg Arenz, Youping Chen +1
Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on…
An Adaptive Human Driver Model for Realistic Race Car Simulations
Stefan Löckel, Siwei Ju, Maximilian Schaller +2
Engineering a high-performance race car requires a direct consideration of the human driver using real-world tests or Human-Driver-in-the-Loop simulations. Apart from that, offline…
Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models
Michael Lutter, Jan Peters
Deep learning has been widely used within learning algorithms for robotics. One disadvantage of deep networks is that these networks are black-box representations. Therefore, the l…
An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients
João Carvalho, Davide Tateo, Fabio Muratore +1
Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate…
High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
Antoine Grosnit, Rasul Tutunov, Alexandre Max Maraval +9
We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces. By…
Robust Value Iteration for Continuous Control Tasks
Michael Lutter, Shie Mannor, Jan Peters +2
When transferring a control policy from simulation to a physical system, the policy needs to be robust to variations in the dynamics to perform well. Commonly, the optimal policy o…
Value Iteration in Continuous Actions, States and Time
Michael Lutter, Shie Mannor, Jan Peters +2
Classical value iteration approaches are not applicable to environments with continuous states and actions. For such environments, the states and actions are usually discretized, w…
Reinforcement Learning using Guided Observability
Stephan Weigand, Pascal Klink, Jan Peters +1
Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems. However, an open question is ho…
SKID RAW: Skill Discovery from Raw Trajectories
Daniel Tanneberg, Kai Ploeger, Elmar Rueckert +1
Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching…
Differentiable Implicit Layers
Andreas Look, Simona Doneva, Melih Kandemir +2
In this paper, we introduce an efficient backpropagation scheme for non-constrained implicit functions. These functions are parametrized by a set of learnable weights and may optio…
Convex Optimization with an Interpolation-based Projection and its Application to Deep Learning
Riad Akrour, Asma Atamna, Jan Peters
Convex optimizers have known many applications as differentiable layers within deep neural architectures. One application of these convex layers is to project points into a convex…
A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning
Hany Abdulsamad, Peter Nickl, Pascal Klink +1
Probabilistic regression techniques in control and robotics applications have to fulfill different criteria of data-driven adaptability, computational efficiency, scalability to hi…
ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows
Julen Urain, Michelle Ginesi, Davide Tateo +1
We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows f…
Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient
Samuele Tosatto, João Carvalho, Jan Peters
Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current…
Active Inference or Control as Inference? A Unifying View
Joe Watson, Abraham Imohiosen, Jan Peters
Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation. However, th…
Data-efficient Domain Randomization with Bayesian Optimization
Fabio Muratore, Christian Eilers, Michael Gienger +1
When learning policies for robot control, the required real-world data is typically prohibitively expensive to acquire, so learning in simulation is a popular strategy. Unfortunate…
MushroomRL: Simplifying Reinforcement Learning Research
Carlo D'Eramo, Davide Tateo, Andrea Bonarini +2
MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments. Compared to other available libra…
A Nonparametric Off-Policy Policy Gradient
Samuele Tosatto, Joao Carvalho, Hany Abdulsamad +1
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is es…
Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning
Simone Parisi, Davide Tateo, Maximilian Hensel +3
Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where th…