mlsanityData to 7 Oct 2026

Safety Guarantees in Zero-Shot Reinforcement Learning for Cascade Dynamical Systems

arXiv 2604.10429 ↗First posted 12 Apr 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper considers the problem of zero-shot safety guarantees for cascade dynamical systems. These are systems where a subset of the states (the inner states) affects the dynamics of the remaining states (the outer states) but not vice-versa. We define safety as remaining on a set deemed safe for all times with high probability. We propose to train a safe RL policy on a reduced-order model, which ignores the dynamics of the inner states, but it treats it as an action that influences the outer state. Thus, reducing the complexity of the training. When deployed in the full system the trained policy is combined with a low-level controller whose task is to track the reference provided by the RL policy. Our main theoretical contribution is a bound on the safe probability in the full-order system. In particular, we establish the interplay between the probability of remaining safe after the zero-shot deployment and the quality of the tracking of the inner states. We validate our theoretical findings on a quadrotor navigation task, demonstrating that the preservation of the safety guarantees is tied to the bandwidth and tracking capabilities of the low-level controller.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

14 of 26 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Constrained Policy Optimizationcited by 928
  3. 2018Reward Constrained Policy Optimizationcited by 397
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  5. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  6. 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 144
  7. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 91
  8. 2019Safe Policies for Reinforcement Learning via Primal-Dual Methodscited by 75
  9. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 24
  10. 2023Probabilistic Constraint for Safety-Critical Reinforcement Learningcited by 11
  11. 2025SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfercited by 8
  12. 2023Safety-Critical Control with Bounded Inputs via Reduced Order Modelscited by 4
2 more
  1. 2023Reinforcement Learning for Reduced-order Models of Legged Robotscited by 3
  2. 2024Transfer Learning for a Class of Cascade Dynamical Systemscited by 1

Built on by

Not cited yet.