15 citations · 20 across the 5 of their papers we have counts for
5 papers
Spatial Reasoning via Deep Vision Models for Robotic Sequential Manipulation
Hongyou Zhou, Ingmar Schubert, Marc Toussaint +1
In this paper, we propose using deep neural architectures (i.e., vision transformers and ResNet) as heuristics for sequential decision-making in robotic manipulation problems. This…
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…
Reinforcement Learning with Neural Radiance Fields
Danny Driess, Ingmar Schubert, Pete Florence +2
It is a long-standing problem to find effective representations for training reinforcement learning (RL) agents. This paper demonstrates that learning state representations with su…
Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics
Ingmar Schubert, Danny Driess, Ozgur S. Oguz +1
Applications of Reinforcement Learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenario…
Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks
Ingmar Schubert, Ozgur S. Oguz, Marc Toussaint
In high-dimensional state spaces, the usefulness of Reinforcement Learning (RL) is limited by the problem of exploration. This issue has been addressed using potential-based reward…