Data-driven regularized least squares with self-normalized bounds and lattice abstraction yields certified (N, ε)-PCIS for linear MDPs via conservative backward recursion.
hub Canonical reference
arXiv preprint arXiv:2205.10330 (2022)
Canonical reference. 100% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 5polarities
background 5representative citing papers
A no-regret procedure for safe online logistic classification that meets a target error rate with high probability using only O(sqrt(T)) excess tests over an oracle.
SafeDec uses constrained decoding to ensure autoregressive robot navigation foundation models generate actions that provably satisfy STL safety specifications under assumed dynamics.
CPSS projects cumulative safety constraints into time-varying per-state thresholds for online action shielding in nonstationary RL, providing per-state guarantees and cumulative bounds.
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.
Introduces KCPR and its deep form klDMP that couples reward and punishment policies via learned priors, yielding improved safety and stability in grid-world and Gazebo navigation tasks over DQN, SQL and softDMP.
LILAC+ combines context-based, adaptation-speed, and budget-to-state safety constraints to reduce violations in continual RL under nonstationary conditions, demonstrated in simulated driving tasks.
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.
SafeVLA applies constrained reinforcement learning via CMDP min-max optimization to VLAs, cutting safety violation costs by 83.58% while preserving task success on long-horizon mobile manipulation tasks.
A reinforcement learning model is ethically fine-tuned using aggregated feedback from LLMs embodying five moral principles via Belief Jensen-Shannon Divergence and Dempster-Shafer Theory.
A literature review of safe RL using Lyapunov and barrier functions that identifies a shift to model-free methods since 2017, well-defined open problems per approach class, and high-dimensional scalability as the main barrier.
citing papers explorer
-
Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making
A reinforcement learning model is ethically fine-tuned using aggregated feedback from LLMs embodying five moral principles via Belief Jensen-Shannon Divergence and Dempster-Shafer Theory.