Publication
Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning
Summary
Frames adaptation feasibility as a safety problem by comparing the rate of environmental change with an agent's effective adaptation capacity and proactively tightening behavior when safe adaptation may be too slow.
adaptation speedsafe reinforcement learningnonstationarityadaptive safetyruntime shielding
Citation information
Timothy Tomashevskiy. “Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning.” 2026. arXiv:2607.21646.
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.