1 citations · 1 across the 4 of their papers we have counts for
7 papers
Diminishing Return of Value Expansion Methods
Daniel Palenicek, Michael Lutter, João Carvalho +3
Model-based reinforcement learning aims to increase sample efficiency, but the accuracy of dynamics models and the resulting compounding errors are often seen as key limitations. T…
ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching
Niklas Funk, Julen Urain, Joao Carvalho +3
Spatial understanding is a critical aspect of most robotic tasks, particularly when generalization is important. Despite the impressive results of deep generative models in complex…
A Hierarchical Approach to Active Pose Estimation
Jascha Hellwig, Mark Baierl, Joao Carvalho +2
Creating mobile robots which are able to find and manipulate objects in large environments is an active topic of research. These robots not only need to be capable of searching for…
Residual Robot Learning for Object-Centric Probabilistic Movement Primitives
Joao Carvalho, Dorothea Koert, Marek Daniv +1
It is desirable for future robots to quickly learn new tasks and adapt learned skills to constantly changing environments. To this end, Probabilistic Movement Primitives (ProMPs) h…
An Analysis of Measure-Valued Derivatives for Policy Gradients
Joao Carvalho, Jan Peters
Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate…
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…