Publication
Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning
Summary
Introduces proactive safety-constraint generation from inferred and forecast environmental context, allowing an agent to adapt constraints before changing conditions lead to unsafe behavior.
AI safetysafe reinforcement learningnonstationaritycontext forecastingproactive safety
Citation information
Tim Tomashevskiy. “Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning.” Conference on Lifelong Learning Agents (CoLLAs 2026), 2026. arXiv:2609.08080.
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.