Tim Hertweck
Tim Hertweck
Google DeepMind
Verified email at
Cited by
Cited by
Data-efficient hindsight off-policy option learning
M Wulfmeier, D Rao, R Hafner, T Lampe, A Abdolmaleki, T Hertweck, ...
International Conference on Machine Learning, 11340-11350, 2021
The challenges of exploration for offline reinforcement learning
N Lambert, M Wulfmeier, W Whitney, A Byravan, M Bloesch, V Dasagi, ...
arXiv preprint arXiv:2201.11861, 2022
Compositional Transfer in Hierarchical Reinforcement Learning
M Wulfmeier, A Abdolmaleki, R Hafner, JT Springenberg, M Neunert, ...
Towards general and autonomous learning of core skills: A case study in locomotion
R Hafner, T Hertweck, P Klöppner, M Bloesch, M Neunert, M Wulfmeier, ...
Conference on Robot Learning, 1084-1099, 2021
Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup
D Schwab, T Springenberg, MF Martins, T Lampe, M Neunert, ...
arXiv preprint arXiv:1902.04706, 2019
Regularized hierarchical policies for compositional transfer in robotics
M Wulfmeier, A Abdolmaleki, R Hafner, JT Springenberg, M Neunert, ...
arXiv preprint arXiv:1906.11228, 2019
Is curiosity all you need? on the utility of emergent behaviours from curious exploration
O Groth, M Wulfmeier, G Vezzani, V Dasagi, T Hertweck, R Hafner, ...
arXiv preprint arXiv:2109.08603, 2021
Disentangled cumulants help successor representations transfer to new tasks
C Grimm, I Higgins, A Barreto, D Teplyashin, M Wulfmeier, T Hertweck, ...
arXiv preprint arXiv:1911.10866, 2019
Representation matters: Improving perception and exploration for robotics
M Wulfmeier, A Byravan, T Hertweck, I Higgins, A Gupta, T Kulkarni, ...
2021 IEEE International Conference on Robotics and Automation (ICRA), 6512-6519, 2021
Simple sensor intentions for exploration
T Hertweck, M Riedmiller, M Bloesch, JT Springenberg, N Siegel, ...
arXiv preprint arXiv:2005.07541, 2020
Skills: Adaptive skill sequencing for efficient temporally-extended exploration
G Vezzani, D Tirumala, M Wulfmeier, D Rao, A Abdolmaleki, B Moran, ...
arXiv preprint arXiv:2211.13743, 2022
Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots
T Lampe, A Abdolmaleki, S Bechtle, SH Huang, JT Springenberg, ...
arXiv preprint arXiv:2312.11374, 2023
Training action selection neural networks using auxiliary tasks of controlling observation embeddings
M Wulfmeier, T Hertweck, M Riedmiller
US Patent App. 18/016,746, 2023
Less is more--the Dispatcher/Executor principle for multi-task Reinforcement Learning
M Riedmiller, T Hertweck, R Hafner
arXiv preprint arXiv:2312.09120, 2023
Replay across Experiments: A Natural Extension of Off-Policy RL
D Tirumala, T Lampe, JE Chen, T Haarnoja, S Huang, G Lever, B Moran, ...
arXiv preprint arXiv:2311.15951, 2023
The system can't perform the operation now. Try again later.
Articles 1–15