4 papers
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele +2
Model-based reinforcement learning (MBRL) infers information about the environment from a learned dynamics model and bears the potential to address open problems such as data effic…
Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
Devdutt Subhasish, Henrik Hose, Sebastian Trimpe
Reinforcement Learning (RL) has the potential to enable robots with fast, nonlinear, and unstable dynamics to reach the limits of their performance. However, most recent advances r…
The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning
Henrik Hose, Paul Brunzema, Devdutt Subhasish +1
The development of robust learning-based control algorithms for unstable systems requires high-quality, real-world data, yet access to specialized robotic hardware remains a signif…
On Rollouts in Model-Based Reinforcement Learning
Bernd Frauenknecht, Devdutt Subhasish, Friedrich Solowjow +1
Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated mo…