Data-driven regularized least squares with self-normalized bounds and lattice abstraction yields certified (N, ε)-PCIS for linear MDPs via conservative backward recursion.
A review of safe reinforcement learning: Methods, theory and applications
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
TwinGate deploys a stateful dual-encoder system with asymmetric contrastive learning to detect decompositional jailbreaks in untraceable LLM traffic at high recall and low false-positive rate with negligible latency.
The authors introduce affine repulsive RL policies that provably satisfy hard affine state constraints for black-box hybrid dynamical systems with affine reset maps by deriving sufficient closed-loop safety conditions and testing on pendulum and juggler examples.
CAMCO enforces policy constraints on multi-agent AI at deployment time via convex projection, risk-weighted Lagrangian shaping, and bounded-convergence negotiation, yielding zero violations and 92-97% utility in tested enterprise scenarios.
citing papers explorer
-
Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear MDPs
Data-driven regularized least squares with self-normalized bounds and lattice abstraction yields certified (N, ε)-PCIS for linear MDPs via conservative backward recursion.
-
TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
TwinGate deploys a stateful dual-encoder system with asymmetric contrastive learning to detect decompositional jailbreaks in untraceable LLM traffic at high recall and low false-positive rate with negligible latency.
-
Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems
The authors introduce affine repulsive RL policies that provably satisfy hard affine state constraints for black-box hybrid dynamical systems with affine reset maps by deriving sufficient closed-loop safety conditions and testing on pendulum and juggler examples.
-
Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
CAMCO enforces policy constraints on multi-agent AI at deployment time via convex projection, risk-weighted Lagrangian shaping, and bounded-convergence negotiation, yielding zero violations and 92-97% utility in tested enterprise scenarios.