Marvin Alles

According to our database, Marvin Alles authored at least 5 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Latent Action World Models for Control with Unlabeled Trajectories.

Marvin Alles, Xingyuan Zhang, Patrick van der Smagt, Philip Becker-Ehmck

CoRR, December, 2025

FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning.

Marvin Alles, Nutan Chen, Patrick van der Smagt, Botond Cseke

CoRR, May, 2025

2024

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning.

Marvin Alles, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Guided Decoding for Robot On-line Motion Generation and Adaption.

Nutan Chen, Botond Cseke, Elie Aljalbout, Alexandros Paraschos, Marvin Alles, Patrick van der Smagt

Proceedings of the 23rd IEEE-RAS International Conference on Humanoid Robots, 2024

2022

Learning to Centralize Dual-Arm Assembly.

Marvin Alles, Elie Aljalbout

Frontiers Robotics AI, 2022