Bernhard Schölkopf
2 papers · Latest:
Machine Learning
Bounded Ratio Reinforcement Learning
This paper introduces Bounded Ratio Reinforcement Learning (BRRL) and BPO, a new algorithm that theoretically guarantees monotonic improvement and empirically outperforms PPO.
2604.18578
RoboticsSim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks
A new sim-to-real pipeline, GeAN, enables successful policy transfer for muscle-actuated robots by learning complex actuation models from joint trajectories.
2604.09487
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.