Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jan Peters

Jan Peters

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×1Robotics×1AI×1

Frequent co-authors

Christian Scherer1×
Joe Watson1×
Theo Gruner1×
Daniel Palenicek1×
Ingmar Posner1×
Nico Bohlinger1×

Research Timeline

2026
Shape Your Body: Value Gradients for Multi-Embodiment Robot Design

The paper introduces using frozen, generalist value functions as differentiable surrogates to efficiently optimize and analyze new multi-embodiment robot designs without requiring repeated reinforcement learning training.

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

The paper proposes a coherent inverse reinforcement learning (IRL) method to improve large behavior models for robotic control, achieving superior sample efficiency and performance on complex sparse manipulation tasks compared to traditional RL baselines.

Highlighted terms show continued research focus across papers

Papers

cs.LGRecentJun 1, 2026

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek +2 more

The paper proposes a coherent inverse reinforcement learning (IRL) method to improve large behavior models for robotic control, achieving superior sample efficiency and performance on complex sparse m…

View →
cs.ROcs.AIRecentMay 30, 2026

Shape Your Body: Value Gradients for Multi-Embodiment Robot Design

Nico Bohlinger, Jan Peters

The paper introduces using frozen, generalist value functions as differentiable surrogates to efficiently optimize and analyze new multi-embodiment robot designs without requiring repeated reinforceme…

View →