Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Markus Wulfmeier

Markus Wulfmeier

Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation


Dec 02, 2021
Todor Davchev, Oleg Sushkov, Jean-Baptiste Regli, Stefan Schaal, Yusuf Aytar, Markus Wulfmeier, Jon Scholz

Figure 1 for Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation
Figure 2 for Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation
Figure 3 for Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation
Figure 4 for Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation

  Access Paper or Ask Questions

Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies


Nov 03, 2021
Tim Seyde, Igor Gilitschenski, Wilko Schwarting, Bartolomeo Stellato, Martin Riedmiller, Markus Wulfmeier, Daniela Rus

Figure 1 for Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies
Figure 2 for Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies
Figure 3 for Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies
Figure 4 for Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies

  Access Paper or Ask Questions

Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration


Sep 17, 2021
Oliver Groth, Markus Wulfmeier, Giulia Vezzani, Vibhavari Dasagi, Tim Hertweck, Roland Hafner, Nicolas Heess, Martin Riedmiller

Figure 1 for Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
Figure 2 for Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
Figure 3 for Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
Figure 4 for Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
* 14 pages, 7 figures, 2 tables 
  Access Paper or Ask Questions

From Motor Control to Team Play in Simulated Humanoid Football


May 25, 2021
Siqi Liu, Guy Lever, Zhe Wang, Josh Merel, S. M. Ali Eslami, Daniel Hennes, Wojciech M. Czarnecki, Yuval Tassa, Shayegan Omidshafiei, Abbas Abdolmaleki, Noah Y. Siegel, Leonard Hasenclever, Luke Marris, Saran Tunyasuvunakool, H. Francis Song, Markus Wulfmeier, Paul Muller, Tuomas Haarnoja, Brendan D. Tracey, Karl Tuyls, Thore Graepel, Nicolas Heess

Figure 1 for From Motor Control to Team Play in Simulated Humanoid Football
Figure 2 for From Motor Control to Team Play in Simulated Humanoid Football
Figure 3 for From Motor Control to Team Play in Simulated Humanoid Football
Figure 4 for From Motor Control to Team Play in Simulated Humanoid Football

  Access Paper or Ask Questions

Representation Matters: Improving Perception and Exploration for Robotics


Nov 03, 2020
Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck, Irina Higgins, Ankush Gupta, Tejas Kulkarni, Malcolm Reynolds, Denis Teplyashin, Roland Hafner, Thomas Lampe, Martin Riedmiller

Figure 1 for Representation Matters: Improving Perception and Exploration for Robotics
Figure 2 for Representation Matters: Improving Perception and Exploration for Robotics
Figure 3 for Representation Matters: Improving Perception and Exploration for Robotics
Figure 4 for Representation Matters: Improving Perception and Exploration for Robotics

  Access Paper or Ask Questions

"What, not how": Solving an under-actuated insertion task from scratch


Oct 30, 2020
Giulia Vezzani, Michael Neunert, Markus Wulfmeier, Rae Jeong, Thomas Lampe, Noah Siegel, Roland Hafner, Abbas Abdolmaleki, Martin Riedmiller, Francesco Nori

Figure 1 for "What, not how": Solving an under-actuated insertion task from scratch
Figure 2 for "What, not how": Solving an under-actuated insertion task from scratch
Figure 3 for "What, not how": Solving an under-actuated insertion task from scratch
Figure 4 for "What, not how": Solving an under-actuated insertion task from scratch

  Access Paper or Ask Questions

Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion


Aug 06, 2020
Roland Hafner, Tim Hertweck, Philipp Klöppner, Michael Bloesch, Michael Neunert, Markus Wulfmeier, Saran Tunyasuvunakool, Nicolas Heess, Martin Riedmiller

Figure 1 for Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
Figure 2 for Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
Figure 3 for Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
Figure 4 for Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion

  Access Paper or Ask Questions

Data-efficient Hindsight Off-policy Option Learning


Jul 30, 2020
Markus Wulfmeier, Dushyant Rao, Roland Hafner, Thomas Lampe, Abbas Abdolmaleki, Tim Hertweck, Michael Neunert, Dhruva Tirumala, Noah Siegel, Nicolas Heess, Martin Riedmiller

Figure 1 for Data-efficient Hindsight Off-policy Option Learning
Figure 2 for Data-efficient Hindsight Off-policy Option Learning
Figure 3 for Data-efficient Hindsight Off-policy Option Learning
Figure 4 for Data-efficient Hindsight Off-policy Option Learning

  Access Paper or Ask Questions

Simple Sensor Intentions for Exploration


May 15, 2020
Tim Hertweck, Martin Riedmiller, Michael Bloesch, Jost Tobias Springenberg, Noah Siegel, Markus Wulfmeier, Roland Hafner, Nicolas Heess

Figure 1 for Simple Sensor Intentions for Exploration
Figure 2 for Simple Sensor Intentions for Exploration
Figure 3 for Simple Sensor Intentions for Exploration
Figure 4 for Simple Sensor Intentions for Exploration

  Access Paper or Ask Questions

Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics


Jan 02, 2020
Michael Neunert, Abbas Abdolmaleki, Markus Wulfmeier, Thomas Lampe, Jost Tobias Springenberg, Roland Hafner, Francesco Romano, Jonas Buchli, Nicolas Heess, Martin Riedmiller

Figure 1 for Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
Figure 2 for Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
Figure 3 for Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
Figure 4 for Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
* Presented at the 3rd Conference on Robot Learning (CoRL 2019), Osaka, Japan. Video: https://youtu.be/eUqQDLQXb7I 
  Access Paper or Ask Questions

Disentangled Cumulants Help Successor Representations Transfer to New Tasks


Nov 25, 2019
Christopher Grimm, Irina Higgins, Andre Barreto, Denis Teplyashin, Markus Wulfmeier, Tim Hertweck, Raia Hadsell, Satinder Singh

Figure 1 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Figure 2 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Figure 3 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Figure 4 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks

  Access Paper or Ask Questions

Attention Privileged Reinforcement Learning For Domain Transfer


Nov 19, 2019
Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell, Ingmar Posner

Figure 1 for Attention Privileged Reinforcement Learning For Domain Transfer
Figure 2 for Attention Privileged Reinforcement Learning For Domain Transfer
Figure 3 for Attention Privileged Reinforcement Learning For Domain Transfer
Figure 4 for Attention Privileged Reinforcement Learning For Domain Transfer

  Access Paper or Ask Questions

Regularized Hierarchical Policies for Compositional Transfer in Robotics


Jun 27, 2019
Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Tim Hertweck, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

Figure 1 for Regularized Hierarchical Policies for Compositional Transfer in Robotics
Figure 2 for Regularized Hierarchical Policies for Compositional Transfer in Robotics
Figure 3 for Regularized Hierarchical Policies for Compositional Transfer in Robotics
Figure 4 for Regularized Hierarchical Policies for Compositional Transfer in Robotics
* Preprint. Under review. Addressed typos 
  Access Paper or Ask Questions

Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation


Apr 15, 2019
Markus Wulfmeier

Figure 1 for Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation
Figure 2 for Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation
Figure 3 for Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation
Figure 4 for Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation
* Dissertation Summary 
  Access Paper or Ask Questions

TACO: Learning Task Decomposition via Temporal Alignment for Control


Aug 10, 2018
Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson, Ingmar Posner

Figure 1 for TACO: Learning Task Decomposition via Temporal Alignment for Control
Figure 2 for TACO: Learning Task Decomposition via Temporal Alignment for Control
Figure 3 for TACO: Learning Task Decomposition via Temporal Alignment for Control
Figure 4 for TACO: Learning Task Decomposition via Temporal Alignment for Control
* 12 Pages. Published at ICML 2018 
  Access Paper or Ask Questions

Reverse Curriculum Generation for Reinforcement Learning


Jul 23, 2018
Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, Pieter Abbeel

Figure 1 for Reverse Curriculum Generation for Reinforcement Learning
Figure 2 for Reverse Curriculum Generation for Reinforcement Learning
Figure 3 for Reverse Curriculum Generation for Reinforcement Learning
Figure 4 for Reverse Curriculum Generation for Reinforcement Learning
* Published at the 1st Conference on Robot Learning (CoRL 2017) 
  Access Paper or Ask Questions

On Machine Learning and Structure for Mobile Robots


Jun 15, 2018
Markus Wulfmeier

* Informal Review 
  Access Paper or Ask Questions

Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing


Jun 15, 2018
Fabian B. Fuchs, Oliver Groth, Adam R. Kosiorek, Alex Bewley, Markus Wulfmeier, Andrea Vedaldi, Ingmar Posner

Figure 1 for Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing
Figure 2 for Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing
Figure 3 for Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing
Figure 4 for Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing

  Access Paper or Ask Questions

Incremental Adversarial Domain Adaptation for Continually Changing Environments


Feb 24, 2018
Markus Wulfmeier, Alex Bewley, Ingmar Posner

Figure 1 for Incremental Adversarial Domain Adaptation for Continually Changing Environments
Figure 2 for Incremental Adversarial Domain Adaptation for Continually Changing Environments
Figure 3 for Incremental Adversarial Domain Adaptation for Continually Changing Environments
Figure 4 for Incremental Adversarial Domain Adaptation for Continually Changing Environments
* International Conference on Robotics and Automation 2018 
  Access Paper or Ask Questions

Mutual Alignment Transfer Learning


Sep 26, 2017
Markus Wulfmeier, Ingmar Posner, Pieter Abbeel

Figure 1 for Mutual Alignment Transfer Learning
Figure 2 for Mutual Alignment Transfer Learning
Figure 3 for Mutual Alignment Transfer Learning
Figure 4 for Mutual Alignment Transfer Learning

  Access Paper or Ask Questions

Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation


Sep 17, 2017
Markus Wulfmeier, Alex Bewley, Ingmar Posner

Figure 1 for Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Figure 2 for Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Figure 3 for Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Figure 4 for Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
* In Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017) 
  Access Paper or Ask Questions

Incorporating Human Domain Knowledge into Large Scale Cost Function Learning


Dec 13, 2016
Markus Wulfmeier, Dushyant Rao, Ingmar Posner

Figure 1 for Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
Figure 2 for Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
Figure 3 for Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
Figure 4 for Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
* Neural Information Processing Systems 2016, Deep Reinforcement Learning Workshop 
  Access Paper or Ask Questions

Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments


Jul 08, 2016
Markus Wulfmeier, Dominic Zeng Wang, Ingmar Posner

Figure 1 for Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments
Figure 2 for Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments
Figure 3 for Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments
Figure 4 for Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments
* Accepted for publication in the Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016) 
  Access Paper or Ask Questions

Maximum Entropy Deep Inverse Reinforcement Learning


Mar 11, 2016
Markus Wulfmeier, Peter Ondruska, Ingmar Posner

Figure 1 for Maximum Entropy Deep Inverse Reinforcement Learning
Figure 2 for Maximum Entropy Deep Inverse Reinforcement Learning
Figure 3 for Maximum Entropy Deep Inverse Reinforcement Learning
Figure 4 for Maximum Entropy Deep Inverse Reinforcement Learning

  Access Paper or Ask Questions