analiza aiqbench
This paper advances safety-critical reinforcement learning by addressing peak-cost constraints, which are essential when even a single catastrophic failure must be prevented. The authors introduce a robust optimization framework that bridges the gap between simulated training and real-world deployment under dynamic perturbations. Their theoretical proofs regarding duality gaps and experimental results demonstrate effective constraint adherence without sacrificing reward performance.
Robust Peak-cost Constrained Reinforcement Learning
arXiv:2607.15457v2 Announce Type: replace Abstract: We study robust peak-cost constrained reinforcement learning (\ours), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory. This setting is motivated by safety-critical applications in which a single large violation can be catastrophic and therefore cannot be adequately captured by the standard CMDP framework based on expected cumulative cost. Existing reachability-constrained RL methods adopt Lagrangian-based approaches, yet the underlying duality properties of peak-cost constrained MDPs remain unclear. We show that, unlike standard CMDPs, peak-cost constrained MDPs may not admit zero duality gap. We further consider a robust formulation to address simulator-to-real-world mismatch in the transition dynamics. To solve this problem, we develop a surrogate optimization framework and a robust value estimation method based on integral probability metrics. We prove that, with appropriate hyperparameter choices, the surrogate solution attains the same robust reward value as the original problem while violating the constraint by at most \(\epsilon\). Experiments show that the proposed method effectively enforces safety under dynamics perturbations while retaining strong reward performance across diverse environments.
Abstract:We study robust peak-cost constrained reinforcement learning (\ours), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory. This setting is motivated by safety-critical applications in which a single large violation can be catastrophic and therefore cannot be adequately captured by the standard CMDP framework based on expected cumulative cost. Existing reachability-constrained RL methods adopt Lagrangian-based approaches, yet the underlying duality properties of peak-cost constrained MDPs remain unclear. We show that, unlike standard CMDPs, peak-cost constrained MDPs may not admit zero duality gap. We further consider a robust formulation to address simulator-to-real-world mismatch in the transition dynamics. To solve this problem, we develop a surrogate optimization framework and a robust value estimation method based on integral probability metrics. We prove that, with appropriate hyperparameter choices, the surrogate solution attains the same robust reward value as the original problem while violating the constraint by at most \(\epsilon\). Experiments show that the proposed method effectively enforces safety under dynamics perturbations while retaining strong reward performance across diverse environments.
Machine Learning (cs.LG)
arXiv:2607.15457 [cs.LG]
(or arXiv:2607.15457v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.15457 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 265 cuvinte
Subiecte conexe
Robust Peak-cost Constrained Reinforcement Learning
arXiv · 20 iul. 2026
Reinforcement Learning on Cost-Constrained Quadrupedal Hardware
arXiv · 30 iul. 2026
RAVEN: Reinforcement-Adaptive Visibility-Graph Planning for Robust Humanoid Navigation with Collision-Free MPC
arXiv · 20 iul. 2026
SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
arXiv · 12 oct. 2026