Philip Becker-Ehmck

12 papers A* 3C 1Journal 8
YearRankTypeTitle / Venue / Authors
2025 J jnl
Latent Action World Models for Control with Unlabeled Trajectories.
CoRR
Marvin Alles, Xingyuan Zhang, Patrick van der Smagt, Philip Becker-Ehmck
2025 J jnl
Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models.
Trans. Mach. Learn. Res.
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
2024 A* conf
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning.
NeurIPS
Marvin Alles, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
2024 J jnl
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning.
CoRR
Marvin Alles, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
2024 J jnl
Overcoming Knowledge Barriers: Online Imitation Learning from Observation with Pretrained World Models.
CoRR
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
2023 A* conf
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models.
NeurIPS
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
2023 J jnl
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models.
CoRR
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
2020 J jnl
Learning to Fly via Deep Model-Based Reinforcement Learning.
CoRR
Philip Becker-Ehmck, Maximilian Karl, Jan Peters, Patrick van der Smagt
2019 J jnl
Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations.
CoRR
Neha Das, Maximilian Karl, Philip Becker-Ehmck, Patrick van der Smagt
2019 A* conf
Switching Linear Dynamics for Variational Bayes Filtering.
ICML
Philip Becker-Ehmck, Jan Peters, Patrick van der Smagt
2019 J jnl
Switching Linear Dynamics for Variational Bayes Filtering.
CoRR
Philip Becker-Ehmck, Jan Peters, Patrick van der Smagt
2019 C conf
Unsupervised Real-Time Control Through Variational Empowerment.
ISRR
Maximilian Karl, Philip Becker-Ehmck, Maximilian Soelch, Djalel Benbouzid, Patrick van der Smagt, Justin Bayer