Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning
Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavior. To address this, we present SAS (Self-Alignment for Safety), a transformer-based framework that enables test-time adaptation in offline safe RL without retraining. In SAS, the main mechanism is self-alignment: at test time, the pretrained agent generates several imagined trajectories and selects those satisfying the Lyapunov condition. These fe
Record details
Published: 29 April 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Architectural Constraints Alignment in AI-assisted, Platform-based Service Development
arXiv · 6 May 2026
No More, No Less: Task Alignment in Terminal Agents
arXiv · 12 May 2026
SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving
arXiv · 13 April 2026
OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
arXiv · 13 April 2026
Semantic Rate-Distortion for Bounded Multi-Agent Communication: Capacity-Derived Semantic Spaces and the Communication Cost of Alignment
arXiv · 10 April 2026
CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
arXiv · 10 April 2026
How to cite this record
ethics.ai (29 April 2026), “Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning,” evidence record 5224, https://ethics.ai/record/5224 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.