10 citations · 22 across the 21 of their papers we have counts for
9 papers · 1 filter
SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
Anselm Paulus, A. René Geist, Vít Musil +3
Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in the…
Stochastic Decision Horizons for Survival-Based Constrained Reinforcement Learning
Nikola Milosevic, Leonard Franz, Daniel Haeufle +3
We propose stochastic decision horizons (SDH), a theoretically grounded framework for survival-based constrained reinforcement learning from per-step violation signals. Rather than…
Epistemically-guided forward-backward exploration
Núria Armengol Urpí, Marin Vlastelica, Georg Martius +1
Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward repres…
Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
Pavel Kolev, Marin Vlastelica, Georg Martius
Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift w…
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers
Anselm Paulus, Georg Martius, Vít Musil
Embedding parameterized optimization problems as layers into machine learning architectures serves as a powerful inductive bias. Training such architectures with stochastic gradien…
Causal Action Influence Aware Counterfactual Data Augmentation
Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica +1
Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demons…
Learning with 3D rotations, a hitchhiker's guide to SO(3)
A. René Geist, Jonas Frey, Mikel Zhobro +2
Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. Th…
Multi-View Causal Representation Learning with Partial Observability
Dingling Yao, Danru Xu, Sébastien Lachapelle +5
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partial…
Offline Diversity Maximization Under Imitation Constraints
Marin Vlastelica, Jin Cheng, Georg Martius +1
There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these a…