Tim Hertweck

23 papers A* 5Misc 1Journal 15Unranked 2
YearRankTypeTitle / Venue / Authors
2025 A* conf
Learning from negative feedback, or positive feedback or both.
ICLR
Abbas Abdolmaleki, Bilal Piot, Bobak Shahriari, Jost Tobias Springenberg, Tim Hertweck, Michael Bloesch, Rishabh Joshi, Thomas Lampe, Junhyuk Oh, Nicolas Heess, Jonas Buchli, Martin A. Riedmiller
2024 A* conf
Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots.
ICRA
Thomas Lampe, Abbas Abdolmaleki, Sarah Bechtle, Sandy H. Huang, Jost Tobias Springenberg, Michael Bloesch, Oliver Groth, Roland Hafner, Tim Hertweck, Michael Neunert, Markus Wulfmeier, Jingwei Zhang, Francesco Nori, Nicolas Heess, Martin A. Riedmiller
2024 J jnl
Preference Optimization as Probabilistic Inference.
CoRR
Abbas Abdolmaleki, Bilal Piot, Bobak Shahriari, Jost Tobias Springenberg, Tim Hertweck, Rishabh Joshi, Junhyuk Oh, Michael Bloesch, Thomas Lampe, Nicolas Heess, Jonas Buchli, Martin A. Riedmiller
2024 A* conf
Replay across Experiments: A Natural Extension of Off-Policy RL.
ICLR
Dhruva Tirumala, Thomas Lampe, José Enrique Chen, Tuomas Haarnoja, Sandy H. Huang, Guy Lever, Ben Moran, Tim Hertweck, Leonard Hasenclever, Martin A. Riedmiller, Nicolas Heess, Markus Wulfmeier
2023 J jnl
Less is more - the Dispatcher/ Executor principle for multi-task Reinforcement Learning.
CoRR
Martin A. Riedmiller, Tim Hertweck, Roland Hafner
2023 J jnl
Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots.
CoRR
Thomas Lampe, Abbas Abdolmaleki, Sarah Bechtle, Sandy H. Huang, Jost Tobias Springenberg, Michael Bloesch, Oliver Groth, Roland Hafner, Tim Hertweck, Michael Neunert, Markus Wulfmeier, Jingwei Zhang, Francesco Nori, Nicolas Heess, Martin A. Riedmiller
2023 J jnl
Replay across Experiments: A Natural Extension of Off-Policy RL.
CoRR
Dhruva Tirumala, Thomas Lampe, José Enrique Chen, Tuomas Haarnoja, Sandy H. Huang, Guy Lever, Ben Moran, Tim Hertweck, Leonard Hasenclever, Martin A. Riedmiller, Nicolas Heess, Markus Wulfmeier
2023 J jnl
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration.
Trans. Mach. Learn. Res.
Giulia Vezzani, Dhruva Tirumala, Markus Wulfmeier, Dushyant Rao, Abbas Abdolmaleki, Ben Moran, Tuomas Haarnoja, Jan Humplik, Roland Hafner, Michael Neunert, Claudio Fantacci, Tim Hertweck, Thomas Lampe, Fereshteh Sadeghi, Nicolas Heess, Martin A. Riedmiller
2022 J jnl
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration.
CoRR
Giulia Vezzani, Dhruva Tirumala, Markus Wulfmeier, Dushyant Rao, Abbas Abdolmaleki, Ben Moran, Tuomas Haarnoja, Jan Humplik, Roland Hafner, Michael Neunert, Claudio Fantacci, Tim Hertweck, Thomas Lampe, Fereshteh Sadeghi, Nicolas Heess, Martin A. Riedmiller
2022 J jnl
The Challenges of Exploration for Offline Reinforcement Learning.
CoRR
Nathan Lambert, Markus Wulfmeier, William F. Whitney, Arunkumar Byravan, Michael Bloesch, Vibhavari Dasagi, Tim Hertweck, Martin A. Riedmiller
2021 A* conf
Data-efficient Hindsight Off-policy Option Learning.
ICML
Markus Wulfmeier, Dushyant Rao, Roland Hafner, Thomas Lampe, Abbas Abdolmaleki, Tim Hertweck, Michael Neunert, Dhruva Tirumala, Noah Y. Siegel, Nicolas Heess, Martin A. Riedmiller
2021 J jnl
Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration.
CoRR
Oliver Groth, Markus Wulfmeier, Giulia Vezzani, Vibhavari Dasagi, Tim Hertweck, Roland Hafner, Nicolas Heess, Martin A. Riedmiller
2021 A* conf
Representation Matters: Improving Perception and Exploration for Robotics.
ICRA
Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck, Irina Higgins, Ankush Gupta, Tejas Kulkarni, Malcolm Reynolds, Denis Teplyashin, Roland Hafner, Thomas Lampe, Martin A. Riedmiller
2020 — conf
Compositional Transfer in Hierarchical Reinforcement Learning.
Robotics: Science and Systems
Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Noah Y. Siegel, Tim Hertweck, Thomas Lampe, Nicolas Heess, Martin A. Riedmiller
2020 J jnl
Data-efficient Hindsight Off-policy Option Learning.
CoRR
Markus Wulfmeier, Dushyant Rao, Roland Hafner, Thomas Lampe, Abbas Abdolmaleki, Tim Hertweck, Michael Neunert, Dhruva Tirumala, Noah Y. Siegel, Nicolas Heess, Martin A. Riedmiller
2020 J jnl
Representation Matters: Improving Perception and Exploration for Robotics.
CoRR
Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck, Irina Higgins, Ankush Gupta, Tejas Kulkarni, Malcolm Reynolds, Denis Teplyashin, Roland Hafner, Thomas Lampe, Martin A. Riedmiller
2020 J jnl
Simple Sensor Intentions for Exploration.
CoRR
Tim Hertweck, Martin A. Riedmiller, Michael Bloesch, Jost Tobias Springenberg, Noah Y. Siegel, Markus Wulfmeier, Roland Hafner, Nicolas Heess
2020 Misc conf
Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion.
CoRL
Roland Hafner, Tim Hertweck, Philipp Klöppner, Michael Bloesch, Michael Neunert, Markus Wulfmeier, Saran Tunyasuvunakool, Nicolas Heess, Martin A. Riedmiller
2020 J jnl
Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion.
CoRR
Roland Hafner, Tim Hertweck, Philipp Klöppner, Michael Bloesch, Michael Neunert, Markus Wulfmeier, Saran Tunyasuvunakool, Nicolas Heess, Martin A. Riedmiller
2019 J jnl
Disentangled Cumulants Help Successor Representations Transfer to New Tasks.
CoRR
Christopher Grimm, Irina Higgins, André Barreto, Denis Teplyashin, Markus Wulfmeier, Tim Hertweck, Raia Hadsell, Satinder Singh
2019 J jnl
Regularized Hierarchical Policies for Compositional Transfer in Robotics.
CoRR
Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Tim Hertweck, Thomas Lampe, Noah Y. Siegel, Nicolas Heess, Martin A. Riedmiller
2019 — conf
Simultaneously Learning Vision and Feature-Based Control Policies for Real-World Ball-In-A-Cup.
Robotics: Science and Systems
Devin Schwab, Jost Tobias Springenberg, Murilo Fernandes Martins, Michael Neunert, Thomas Lampe, Abbas Abdolmaleki, Tim Hertweck, Roland Hafner, Francesco Nori, Martin A. Riedmiller
2019 J jnl
Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup.
CoRR
Devin Schwab, Jost Tobias Springenberg, Murilo F. Martins, Thomas Lampe, Michael Neunert, Abbas Abdolmaleki, Tim Hertweck, Roland Hafner, Francesco Nori, Martin A. Riedmiller