Publications (13)
Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots
Thomas Lampe, Abbas Abdolmaleki, Sarah Bechtle +12
Reinforcement learning solely from an agent's self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done…
A Generalist Dynamics Model for Control
Ingmar Schubert, Jingwei Zhang, Jake Bruce +7
We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, bo…
Model-Based Inverse Reinforcement Learning from Visual Demonstrations
Neha Das, Sarah Bechtle, Todor Davchev +3
Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good d…
Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities
Markus Wulfmeier, Arunkumar Byravan, Sarah Bechtle +2
Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by the growth of required resources, expansive datasets and corresponding investments int…
Leveraging Forward Model Prediction Error for Learning Control
Sarah Bechtle, Bilal Hammoud, Akshara Rai +2
Learning for model based control can be sample-efficient and generalize well, however successfully learning models and controllers that represent the problem at hand can be challen…
Curious iLQR: Resolving Uncertainty in Model-based RL
Sarah Bechtle, Yixin Lin, Akshara Rai +2
Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for lear…