Bernd Frauenknecht — accepted AI-conference papers

2025

On Rollouts in Model-Based Reinforcement Learning

Bernd Frauenknecht, Devdutt Subhasish, Friedrich Solowjow, Sebastian Trimpe

ICLR 2025poster

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 model errors during these rollouts can distort the data distribution, negatively impacting policy learning and hindering l…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption

Bernd Frauenknecht, Artur Eisele, Devdutt Subhasish, Friedrich Solowjow, Sebastian Trimpe

ICML 2024poster

Dyna-style model-based reinforcement learning (MBRL) combines model-free agents with predictive transition models through model-based rollouts. This combination raises a critical question: “When to trust your model?”; i.e., which rollout length results in the model providing useful data? Janner et a…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗