3 papers
cs.RO2026
LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors
Loukas Kordos, Leonard T. Franz, Simon Rappenecker +4
Learning-based quadrupedal locomotion typically relies on complex reward formulations that entangle task specification, operational limits, gait preference, and terrain adaptation…
cs.LG2026
Stochastic Decision Horizons for Constrained Reinforcement Learning
Nikola Milosevic, Leonard Franz, Daniel Haeufle +3
We propose stochastic decision horizons (SDH), a theoretically grounded framework for solving constrained RL problems with every-step constraint satisfaction, a desirable property…
cs.LG2026
Drifting Fields are not Conservative
Leonard T. Franz, Sebastian Hoffmann, Tim Weiland +2
Drifting models have recently gained attention for generating high-quality samples in a single forward pass. During training, they learn a push-forward map by following a vector-va…