3 papers
cs.LG2025
Latent Action World Models for Control with Unlabeled Trajectories
Marvin Alles, Xingyuan Zhang, Patrick van der Smagt +1
Inspired by how humans combine direct interaction with action-free experience (e.g., videos), we study world models that learn from heterogeneous data. Standard world models typica…
cs.LG2024
Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt +1
Pretraining and finetuning models has become increasingly popular in decision-making. But there are still serious impediments in Imitation Learning from Observation (ILfO) with pre…
cs.LG2023
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt +1
Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely obser…