Safe Reinforcement Learning via Probabilistic Option Shielding
arXiv:2611.09197v1 Announce Type: new Abstract: Shielding is a safe reinforcement learning technique that provides safety guarantees while learning, by blocking unsafe actions. Traditional shielding relies on a complete model of the environment to provide long-term guarantees. Probabilistic logic shielding (PLS)…
Excerpt provided by arXiv cs.AI via its public feed. Full reporting belongs to the original publisher.
Read the full story on arXiv cs.AI
Related coverage
TechCrunch AI · 1m ago
PSI is trying to make a business out of AI-driven scientific discovery
The Decoder · 46m ago
Gemini 4 Carbon arrives just in time to feel like yesterdays news in the fastest model cycle yet
Ars Technica AI · 4h ago
DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
Google DeepMind · 7h ago
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth