29 citations · 121 across the 63 of their papers we have counts for
8 papers · 1 filter
CIG: Exploration via Conditional Information Gain
Tim Joseph, Marcus Fechner, Philipp Stegmaier +2
Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong rewards score each transition against accumulated experience but ignore within…
Segment to Focus: Guiding Latent Action Models in the Presence of Distractors
Marcus Fechner, Hamza Adnan, Constantin C. Lüth +3
Latent action models (LAMs) offer a promising path to pre-training embodied agents on large amounts of action-free video. They infer latent actions between consecutive observations…
MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations
Daniel Bogdoll, Yitian Yang, Tim Joseph +2
World models for autonomous driving have the potential to dramatically improve the reasoning capabilities of today's systems. However, most works focus on camera data, with only a…
Traffic Scene Similarity: a Graph-based Contrastive Learning Approach
Maximilian Zipfl, Moritz Jarosch, J. Marius Zöllner
Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles. Scenario-based testing offers a potential solu…
Unscented Autoencoder
Faris Janjoš, Lars Rosenbaum, Maxim Dolgov +1
The Variational Autoencoder (VAE) is a seminal approach in deep generative modeling with latent variables. Interpreting its reconstruction process as a nonlinear transformation of…
Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree Search
Karl Kurzer, Matthias Bitzer, J. Marius Zöllner
Cooperative trajectory planning methods for automated vehicles can solve traffic scenarios that require a high degree of cooperation between traffic participants. However, for coop…
Cycle-Consistent World Models for Domain Independent Latent Imagination
Sidney Bender, Tim Joseph, Marius Zoellner
End-to-end autonomous driving seeks to solve the perception, decision, and control problems in an integrated way, which can be easier to generalize at scale and be more adapting to…
Safe Continuous Control with Constrained Model-Based Policy Optimization
Moritz A. Zanger, Karam Daaboul, J. Marius Zöllner
The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic n…