SOURCE-LINKED INTELLIGENCE

Safe Meta-Reinforcement Learning via Information Space Reachability

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL in real-world tasks is hindered by safety requirements, which have been underexplored in prior work. In this paper, we propose a safe meta-RL framework that explicitly accounts for safety during adaptation. Our key insight is to reason about safety in the information space, which captures both the physical state and the agent's belief over the underlying task. Within this space, we introduce a safety value function that measures the probability

Read original source ↗ Open in workspace

recordType

paper

region

Global