Abdullah Tokmak, Kiran Krishnan, Thomas Schön, and Dominik Baumann applied their safe Bayesian optimization algorithm to optimize reinforcement learning policies on physics simulators and a real inverted pendulum, demonstrating improved performance, safety, and scalability compared to state-of-the-art methods.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (1)

• reinforcement learning concept