4 papers
Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning
Tim Tomashevskiy
Ensuring safety in reinforcement learning under nonstationarity requires anticipating changes in risk before they lead to unsafe behavior. Existing approaches typically rely on saf…
Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints
Timofey Tomashevskiy
Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinforcement learning methods oft…
From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning
Timofey Tomashevskiy
Safety in reinforcement learning is often specified through cumulative cost constraints, but these trajectory-level guarantees do not directly prevent unsafe individual decisions,…
Safe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Art
Timofey Tomashevskiy
This work provides a state-of-the-art survey of continual safe online reinforcement learning (COSRL) methods. We discuss theoretical aspects, challenges, and open questions in buil…