We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen …
Designing physical artifacts that serve a purpose---such as tools and other functional structures---is central to engineering as well as everyday human behavior. Though …
M Lutter, J Peters - The International Journal of Robotics …, 2023 - journals.sagepub.com
Deep learning has been widely used within learning algorithms for robotics. One disadvantage of deep networks is that these networks are black-box representations …
Model-based reinforcement learning (MBRL) is a sample efficient technique to obtain control policies, yet unavoidable modeling errors often lead performance deterioration. The model …
State of the art reinforcement learning has enabled training agents on tasks of ever increasing complexity. However, the current paradigm tends to favor training agents from …
Many real-world offline reinforcement learning (RL) problems involve continuous-time environments with delays. Such environments are characterized by two distinctive features …
Monte Carlo methods have become increasingly relevant for control of non-differentiable systems, approximate dynamics models, and learning from data. These methods scale to …
Reinforcement learning (RL) is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample …
We consider the Imitation Learning (IL) setup where expert data are not collected on the actual deployment environment but on a different version. To address the resulting …