Publication
From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning
Summary
Develops CPSS, a runtime mechanism that projects cumulative safety requirements into local action-level constraints, connecting longer-horizon safety budgets to enforceable runtime control.
runtime safetysafe reinforcement learningCPSSconstraint projectionnonstationarity
Citation information
Timofey Tomashevskiy. “From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning.” 2026. arXiv:2605.18841.
The author-name form above follows the corresponding publication/preprint record. Tim Tomashevskiy also publishes under Timofey Tomashevskiy and Timothy Tomashevskiy.
Related research
This work forms part of a broader research program on adaptive AI safety, safe continual reinforcement learning, nonstationarity, and runtime assurance.