Efficient Use of Incorrectly Parameterized Simulators for Robust Real-World Performance

Develop methods that enable robots to efficiently use simulators with incorrect physical parameterization to learn either a control policy or a stochastic world model that achieves robust real-world performance upon deployment.

Background

The authors argue that minimizing the sim-to-real performance gap is often more practical than eliminating the reality gap, suggesting a focus on learning models that improve control near high-return regions rather than uniformly accurate physics. Prior work shows that optimizing controllers for performance under uncertain parameters can outperform planning with most-likely estimates.

This motivates an open question about principled strategies for exploiting imperfect simulators to learn policies or world models that remain robust when transferred to real hardware.

References

As such, an open question remains as to how a robot can most efficiently use a simulator with incorrect parametrization to learn either a policy or stochastic world model for use in generating robust, real-world performance.

— The Reality Gap in Robotics: Challenges, Solutions, and Best Practices  (2510.20808 - Aljalbout et al., 23 Oct 2025) in Section 7.1 (Wrong Models, Better Controllers)

Although the resulting HRRL mechanism is unusually transparent, its behavior under learned or misspecified body dynamics remains an open empirical question.

— Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experience  (2608.27843 - Chen et al., 28 Aug 2026) in Section 6, Limitations