Alert button
Picture for Georg Martius

Georg Martius

Alert button

Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision

Add code
Bookmark button
Alert button
Apr 10, 2024
Matías Mattamala, Jonas Frey, Piotr Libera, Nived Chebrolu, Georg Martius, Cesar Cadena, Marco Hutter, Maurice Fallon

Viaarxiv icon

Learning to Control Emulated Muscles in Real Robots: Towards Exploiting Bio-Inspired Actuator Morphology

Add code
Bookmark button
Alert button
Feb 08, 2024
Pierre Schumacher, Lorenz Krause, Jan Schneider, Dieter Büchler, Georg Martius, Daniel Haeufle

Viaarxiv icon

Colored Noise in PPO: Improved Exploration and Performance Through Correlated Action Sampling

Add code
Bookmark button
Alert button
Dec 18, 2023
Jakob Hollenstein, Georg Martius, Justus Piater

Viaarxiv icon

Regularity as Intrinsic Reward for Free Play

Add code
Bookmark button
Alert button
Dec 03, 2023
Cansu Sancaktar, Justus Piater, Georg Martius

Figure 1 for Regularity as Intrinsic Reward for Free Play
Figure 2 for Regularity as Intrinsic Reward for Free Play
Figure 3 for Regularity as Intrinsic Reward for Free Play
Figure 4 for Regularity as Intrinsic Reward for Free Play
Viaarxiv icon

Goal-conditioned Offline Planning from Curious Exploration

Add code
Bookmark button
Alert button
Nov 28, 2023
Marco Bagatella, Georg Martius

Viaarxiv icon

Multi-View Causal Representation Learning with Partial Observability

Add code
Bookmark button
Alert button
Nov 07, 2023
Dingling Yao, Danru Xu, Sébastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius von Kügelgen, Francesco Locatello

Viaarxiv icon

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

Add code
Bookmark button
Alert button
Oct 03, 2023
Jin Cheng, Marin Vlastelica, Pavel Kolev, Chenhao Li, Georg Martius

Figure 1 for Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Figure 2 for Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Figure 3 for Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Figure 4 for Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Viaarxiv icon

Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks

Add code
Bookmark button
Alert button
Sep 22, 2023
Sina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis, Tim Jakob Schäfer, Georg Martius, Anna Levina

Figure 1 for Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Figure 2 for Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Figure 3 for Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Figure 4 for Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Viaarxiv icon

Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

Add code
Bookmark button
Alert button
Sep 11, 2023
Marin Vlastelica, Sebastian Blaes, Cristina Pineri, Georg Martius

Figure 1 for Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning
Figure 2 for Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning
Figure 3 for Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning
Figure 4 for Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning
Viaarxiv icon

Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models

Add code
Bookmark button
Alert button
Sep 07, 2023
Pierre Schumacher, Thomas Geijtenbeek, Vittorio Caggiano, Vikash Kumar, Syn Schmitt, Georg Martius, Daniel F. B. Haeufle

Figure 1 for Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
Figure 2 for Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
Figure 3 for Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
Figure 4 for Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
Viaarxiv icon